Since dynamic power has a quadratic relationship with voltage, reducing voltage is an effective way to lower power consumption in digital circuits. However, maintaining stable operation at lower voltages is challenging due to increased sensitivity to Process, Voltage, and Temperature (PVT) variations, making it difficult to determine optimal operating points using Static Timing Analysis (STA). While circuit-and device-level solutions like Timing Error Detection (TED) systems can enable lower voltage operation, they introduce significant overhead and design complexity. In this paper, we integrate an Algorithm-Based Fault Detection (ABFT) method into the structure of systolic arrays to capture timing errors when voltage is scaled down, ensuring safe and optimized low-voltage operation. Our proposed approach, SCISSORS, demonstrates how extra voltage margins in systolic arrays used for matrix arithmetic can be trimmed by integrating a simple algorithmic technique into the structure of the array. This solution not only detects errors in the accelerator but also those caused by voltage reduction in on-chip memory and auxiliary circuits. It is fully implementable through HDL without requiring transistor-or circuit-level modifications to the netlist. Implementation on a Zynq System-on-Chip (SoC) shows that SCISSORS introduces only a tolerable overhead of 11% and 8% for 32×32 and 64×64 systolic arrays, respectively, while achieving nearly a 2× improvement in energy efficiency. Experimental results further demonstrate that SCISSORS adaptively adjusts voltage in response to the voltage-temperature coupling behavior of digital circuits at runtime, specifically addressing Inverse Temperature Dependence (ITD).

Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this field has seen recent progress, it remains an active exploration area. This paper aims to provide a comprehensive and systematic review of FSCIL. In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL). Besides, we offer an overview of benchmark datasets and evaluation metrics. Furthermore, we introduce the Few-shot Class-incremental Classification (FSCIC) methods from data-based, structure-based, and optimization-based approaches and the Few-shot Class-incremental Object Detection (FSCIOD) methods from anchor-free and anchor-based approaches. Beyond these, we present several promising research directions within FSCIL that merit further investigation.

Millimeter (mmWave) beamforming is an integral component of fifth-generation (5G) and beyond radio commu-nications. 5G beamforming involves the initial beam selection procedure using a codebook with multiple radio beam directions. Conventional codebook-based alignment schemes involve exhaustive sweeping over the predefined beam directions, the number of which increases significantly with large numbers of antennas resulting in undesirable latency and communications signal overhead. In this paper, we propose a novel algebraic-based codebook using Gröbner basis polynomial solvers to reduce the signal overhead during beam alignment. We also analyze the complexity-performance tradeoff between the proposed algebraic-based codebook and the exhaustive-based beam alignment across different monomial thresholds, multiple antenna configurations and radio contextual location information. Our results show that the proposed approach reduces the beam-search overhead at an average complexity reduction ratio of 73.95% with a performance tradeoff error of 32.25%.

In-process hot-rolled strip steel is suffering from some complicated yet unavoidable surface defects due to its harsh production environment. The automated visual inspection on defects consistently faces challenges of interclass similarity, intraclass difference, low contrast, and overlapping issue, which tend to trigger false or missed detections. This article proposes a prior-modulated and semantic-aligned dynamic transformer, called PMSA-DyTr. In this framework, a long short-term self-attention embedded with local convolution is designed for assisting an encoder to eliminate noise ambiguity between defects and backgrounds. Then, a semantic aligner is cleverly bridged between the encoder and the decoder to align the sematic for speeding up the convergence, and prior-modulated cross attention is proposed to alleviate the deficiency of samples for a data-driven transformer. Furthermore, a gate controller is innovatively constructed to dynamically select the minimal number of encoder blocks while preserving detection accuracy. The proposed PMSA-DyTr outperforms 19 state-of-the-art models on mean average precision with an inference time of 54.67 ms and visually performs best in detecting low-contrast and multiple small defects.

Remote photoplethysmography (rPPG) offers a state-of-the-art, non-contact methodology for estimating human pulse by analyzing facial videos. Despite its potential, rPPG methods can be susceptible to various artifacts, such as noise, occlusions, and other obstructions caused by sunglasses, masks, or even involuntary face touching. In this study, we apply image processing transformations to intentionally degrade video quality, mimicking these challenging conditions, and subsequently evaluate the performance of both non-learning and learning-based rPPG methods on the deteriorated data. Our results reveal a significant decrease in accuracy in the presence of these artifacts, prompting us to propose the application of restoration techniques, such as denoising and inpainting, to improve heart-rate estimation outcomes. By addressing these challenging conditions and occlusion artifacts, our approach aims to make rPPG methods more robust and adaptable to real-world situations. To assess the effectiveness of our proposed methods, we undertake comprehensive experiments on three publicly available datasets, encompassing a wide range of scenarios and artifact types. Our findings underscore the potential to construct a robust rPPG system by employing an optimal combination of restoration algorithms and rPPG techniques. Moreover, our study contributes to the advancement of privacy-conscious rPPG methodologies, thereby bolstering the overall utility and impact of this innovative technology in the field of remote heart-rate estimation under realistic and diverse conditions.

We propose a new power amplifier (PA) behavioral modeling approach, to characterize and compensate for the signal quality degrading effects induced by a PA with a machine learning (ML) aided piece-wise (PW) modeling approach. Instead of using a single pruned Volterra model, we use multiple small-size pruned Volterra models by classifying the input data into different classes. For that purpose, an ML classifier model is trained by extracting some crucial features from both the input signal statistics and the PA operating point. The simulation results indicate that our approach contributes to an improved performance/complexity trade-off than a single generalized memory polynomial (GMP) model in terms of PA behavior modeling and linearization.

In the age of the Internet of Things (IoT) and the expanding computing continuum, it’s crucial to manage and share resources at the edges of networks. This position paper presents a new concept known as ’semantic slicing’. This approach harnesses the power of artificial intelligence (AI), wireless networks, edge computing, and sensing technologies to enable novel applications, optimize resource allocation, and streamline data processing and decision-making across complex systems spanning the computing continuum. Semantic slicing applies a deep understanding of the data and specific application requirements to intelligently allocate resources and distribute processing tasks in the computing continuum. This strategy allows for the creation of systems that are not only more efficient and responsive, but also better equipped to adapt to a variety of applications and services.

Unmanned aerial vehicles (UAVs) are the emerging vital components of millimeter wave (mmWave) wireless systems. Accurate beam alignment is essential for efficient beam based mmWave communications of UAVs with base stations (BSs). Conventional beam sweeping approaches often have large overhead due to the high mobility and autonomous operation of UAVs. Learning-based approaches greatly reduce the overhead by leveraging UAV data, like position to identify optimal beam directions. In this paper, we propose a deep Q-Network(DQN)-based framework for uplink UAV-BS beam alignment where the UAV hovers around 5G new radio (NR) BS coverage area, with varying channel conditions. The proposed learning framework uses the location information and maximize the beamforming gain upon every communication request from UAV inside the multi-location environment. We compare the proposed framework against multi-armed bandit (MAB)-based and exhaustive approaches, respectively and then analyse its training performance over different coverage area requirements, antenna configurations and channel conditions. Our results show that the proposed framework converge faster than the MAB-based approach and comparable to traditional exhaustive approach in an online manner under real-time conditions. Moreover, this approach can be further enhanced to predict the optimal beams for unvisited UAV locations inside the coverage using correlation from neighbouring grid locations.

We explore the possibility of leveraging radar-based sensing systems to analyze vital signs for classification, user identification, and regression tasks. Specifically, we extract time-domain and frequency-domain features from distance, respiration, and pulse signals obtained by filtering radio-frequency signals. Our Random Forest classification models are trained on these features to recognize scenarios in which the radar data were collected, categorize individuals into age groups, and classify human activities. For classification, we achieved up to 94.7% of accuracy when distinguishing apnea and normal breathing in the lying position. We then show the feasibility of identifying individuals in a small group using vital signs, which can support model fine-tuning with data acquired from new users. Furthermore, we used a Random Forest regression model to estimate the Body Mass Index, height, and weight of subjects. These classification, identification, and regression models benefit smart systems that can simultaneously identify users, recognize their behaviours, and extract their vital signs from radar sensors.

Unmanned aerial vehicles (UAVs) are the vital components of sixth generation (6G) millimeter wave (mmWave) wireless networks. Fast and reliable beam alignment is essential for efficient beam-based mmWave communications between UAVs and the base stations (BSs). Learning-based approaches may greatly reduce the overhead by leveraging UAV data, such as position, to identify the optimal beam directions. In this paper, we propose a deep reinforcement learning (DRL)-based framework for UAV-BS beam alignment using the hierarchical deep Q-Network (hDQN) in a mmWave radio setting. We consider uplink communications where the UAV hovers around 5G new radio (NR) BS coverage area, with three dimensional (3D) beams under diverse channel conditions. A BS serves with learnt beam-pairs in an uplink manner upon every communication request from UAV inside the multi-location environment. Compared to our prior DQN-based method, the proposed hDQN framework uses the location information and the fixed spatial arrangement of the antenna elements to reduce the beam search complexity and maximize the data rates efficiently. The results show that our proposed hDQN-based framework converges faster than the DQN-based approach with an average overall training reduction of 43% and, is generic to multi-location environments across different uniform planar array (UPA) configurations and diverse channel conditions.

Chip manufacturers define voltage margins on top of the “best-case” operational voltage of their chips to ensure reliable functioning in the worst-case settings. The margins guarantee correctness of operation, but at the cost of performance and power efficiency. Violating the margins is tempting to save energy, but might lead to timing errors. This article proposes an algorithmic solution that enables reliable removal of the margins by detecting errors on the fly. In contrast to previous approaches that require special hardware to detect timing errors, the proposed method is fully implementable using high-level synthesis tools without reliance on additional hardware. The approach is demonstrated using a$32 \times 32$matrix-matrix multiplication and a simple multilayer neural network implemented on two Xilinx ZC702 field-programmable gate array (FPGA) System-on-Chip (SoC) platforms, showcasing its utility in detecting errors that may originate from different sources of logic circuits, clock tree, or memory. Results show that the energy dissipation is halved, while the implementation is clocked at 2.5x faster than specified by the design tool of the vendor.

Unmanned aerial vehicles (UAVs) are the emerging vital components of millimeter wave (mmWave) wireless systems. Accurate beam alignment is essential for efficient beam based mmWave communications of UAVs with base stations (BSs). Conventional beam sweeping approaches often have large overhead due to the high mobility and autonomous operation of UAVs. Learning-based approaches greatly reduce the overhead by leveraging UAV data, like position to identify optimal beam directions. In this paper, we propose a reinforcement learning (RL)-based framework for UAV-BS beam alignment using deep Q-Network (DQN) in a mmWave setting. We consider uplink communications where the UAV hovers around 5G new radio (NR) BS coverage area, with varying channel conditions. The proposed learning framework uses the location information to maximize data rate through the optimal beam-pairs efficiently, upon every communication request from UAV inside the multi-location environment. We compare our proposed framework against Multi-Armed Bandit (MAB) learning-based approach and the traditional exhaustive approach, respectively and also analyse the training performance of DQN-based beam alignment over different coverage area requirements and channel conditions. Our results show that the proposed DQN-based beam alignment converge faster and generic for different environmental conditions. The framework can also learn optimal beam alignment comparable to the exhaustive approach in an online manner under real-time conditions.

Inspired by the success of classical neural networks, there has been tremendous effort to develop classical effective neural networks into quantum concept. In this paper, a novel hybrid quantum-classical neural network with deep residual learning (Res-HQCNN) is proposed. We firstly analyse how to connect residual block structure with a quantum neural network, and give the corresponding training algorithm. At the same time, the advantages and disadvantages of transforming deep residual learning into quantum concept are provided. As a result, the model can be trained in an end-to-end fashion, analogue to the backpropagation in classical neural networks. To explore the effectiveness of Res-HQCNN , we perform extensive experiments for quantum data with or without noisy on classical computer. The experimental results show the Res-HQCNN performs better to learn an unknown unitary transformation and has stronger robustness for noisy data, when compared to state of the arts. Moreover, the possible methods of combining residual learning with quantum neural networks are also discussed.

Millimeter-wave (mmWave) multiple-input multiple-output (MIMO) system for the fifth generation (5G) cellular communications can also enable single-anchor positioning and object tracking due to its large bandwidth and inherently high angular resolution. In this paper, we introduce the newly invented concept, large intelligent surface (LIS), to mmWave positioning systems, study the theoretical performance bounds (i.e., Cramér-Rao lower bounds) for positioning, and evaluate the impact of the number of LIS elements and the value of phase shifters on the position estimation accuracy compared to the conventional scheme with one direct link and one non-line-of-sight path. It is verified that better performance can be achieved with a LIS from the theoretical analyses and numerical study.

We propose a decision triggered data transmission and collection (DTDTC) protocol for condition monitoring and anomaly detection in the industrial Internet of things (IIoT). In the IIoT, the collection, processing, encoding, and transmission of the sensor readings are usually not for the reconstruction of the original data but for decision making at the fusion center. By moving the decision making process to the local end devices, the amount of data transmission can be significantly reduced, especially when normal signals with positive decisions dominate in the whole life cycle and the fusion center is only interested in collecting the abnormal data. The proposed concept combines compressive sensing, machine learning, data transmission, and joint decision making. The sensor readings are encoded and transmitted to the fusion center only when abnormal signals with negative decisions are detected. All the abnormal signals from the end devices are gathered at the fusion center for a joint decision with feedback messages forwarded to the local actuators. The advantage of such an approach lies in that it can significantly reduce the volume of data to be transmitted through wireless links. Moreover, the introduction of compressive sensing can further reduce the dimension of data tremendously. An exemplary case, i.e., diesel engine condition monitoring, is provided to validate the effectiveness and efficiency of the proposed scheme compared to the conventional ones.

The era of mobile communications and the Internet of Things (IoT) has introduced numerous challenges for mobile processing platforms that are responsible for increasingly complex signal processing tasks from different application domains. In recent years, the power efficiency of computing has been improved by adding more parallelism and workload-specific computing resources to such platforms. However, programming of parallel systems can be time-consuming and challenging if only low-level programming methods are used. This work presents a dataflow-based co-design framework TTADF that reduces the design effort of both software and hardware design for mobile processing platforms. The paper presents three application examples from the fields of video coding, machine vision, and wireless communications. The application examples are mapped and profiled both on a pipelined and a shared-memory multicore platform that is generated by TTADF. The results of the TTADF co-design-based solutions are compared against previous manually created designs and a recent dataflow-based design flow, showing that TTADF provides very high energy efficiency together with a high level of automation in software and hardware design.

High Efficiency Video Coding (HEVC) in-loop filtering includes the deblocking filter (DF) and the sample adaptive offset filter which consume about 20% of the total HEVC de coding time. In this paper a very energy efficient programmable multicore coprocessor for HEVC in-loop filtering is proposed. The coprosessor is placed and routed using leading edge 28nm technology to show that it can be clocked at 1.2 GHz while power consumption is only 207mW including memories. The design is able to filter 101 1080p intra frames per second. The cores can be reprogrammed using a high level language which enables use the high performance coprocessor also for other signal processing algorithms. The proposed coprocessor offers a new alternative between fixed accelerators and general purpose processors for mobile devices in terms of energy efficiency and programmability.

The High Efficiency Video Coding (HEVC) in-loop filtering is designed to reduce coding artifacts caused by image transforms and quantizations. HEVC in-loop filtering is divided to the deblocking filter and the sample adaptive offset filter, and these two filters take about 20% of total decoding time. This paper presents a very low-power (39 mW) programmable coprocessor architecture to HEVC in-loop filtering, targeting especially embedded devices. The solution consists of three identical tiny application specific instruction set processor cores that are able to process 30 Full-HD intra-luma frames/s when the operating frequency is 350 MHz. The cores are fully programmable by C-language, which allows easy software modifications and updates. Although the cores have been designed for in-loop filtering, they are also capable of signal processing tasks that demand high performance. In terms of energy efficiency, the proposed architecture falls clearly between application-specified integrated circuits and conventional embedded processors, and thus forms a new-generation solution for HEVC in-loop filtering.

Exposed-datapath architectures yield small, low-power processors that trade instruction word length for aggressive compile-time scheduling and a high degree of instruction-level parallelism. In this paper, we present a general-purpose parallel accelerator consisting of a main processor and eight symmetric clusters, all in a single core. Use of a lightweight and memory-efficient application programming interface allows for the first high-performance program executing both sequential and data-parallel code on the same TTA processor. We use the processor for LDPC encoding, a popular method of forward error correction. Demonstrating the flexibility of software-defined radio, we benchmark the processor with two programs, one which can handle almost any sort of LDPC code, and another which is optimized for a specific standard. We achieve a throughput of 5 Mb/s with the flexible program and 92 Mb/s with the standard-specific one, while consuming only 95 mW at a clock frequency of 1175 MHz.

Programmable MIMO-OFDM detector design, benchmarking and comparison of implementations have been considered in this paper. We emphasize the significance of co-optimizing the algorithm, software and hardware together in order to reach demanding energy, latency and area restrictions introduced in current standards. We compare energy consumption of the detection algorithms based on the theoretical complexities in function of signal-to-noise ratio. Applying co-optimizing we show how a carefully designed programmable architecture can achieve the 3G long term evolution (LTE) detection rate requirements with a reasonable energy consumption.

CAL is a dataflow oriented language for writing high-level specifications of signal processing applications. The language has recently been standardized and selected for the new MPEG Reconfigurable Video Coding standard. Application specifications written in CAL can be transformed into executable implementations through development tools. Unfortunately, the present tools provide no way to schedule the CAL entities efficiently at run-time. This paper proposes an automated approach to analyze specifications written in CAL, and produce run-time schedules that perform on average 1.45× faster than implementations relying on default scheduling. The approach is based on quasi-static scheduling, which reduces conditional execution in the run-time system.

In this paper, we investigate the opportunities offered by floating-point arithmetics in enabling an assembly and intrinsics free high-level language based development. We compare the characteristics of floating- and fixed-point arithmetics by simulating a MIMO-OFDM soft output detector in a 3G LTE link level simulator. The hardware complexity and energy dissipation are analyzed by implementing three programmable processors supporting 32- and 12-bit floating-point and 16-bit fixed-point arithmetics. The processors are based on the transport triggered architecture (TTA) that has a very low programmability overhead. The analysis shows that at the same goodput rate a floating-point implementation can achieve a lower gate count and better power efficiency than a fixed-point design.

Shooting videos with a hand-held camera introduces shaking, which incontrovertibly reduces video quality. Digital video stabilization is a process to compensate for camera motion by means of image processing. In the best case, it not only removes the image motion, but also reduces image distortion caused by unintentional camera motion. In practice, removing solely unwanted jitter cannot be achieved precisely. Furthermore, the stabilization process itself often introduces some additional distortion in images instead of removing it. In this paper, various means to automatically evaluate the performance of the video stabilization process are proposed, based on measuring the divergence and jitter of the remaining unintentional motion and blurring using point spread function (PSF). This helps, for example, in tuning the system parameters for better quality

In this paper, the computation of likelihood of block motion candidates is considered. The method is based on the evaluation of the sum of squared differences (SSD) measure for local displacements and probabilistic interpretation of these values using local gradient information. Simulated motion data is used to estimate parameters of conditional SSD distributions. The application of our novel likelihood function is demonstrated in a task of dominant motion estimation, where particle filtering is used to maintain a set of global motion hypotheses. In this task, the block motion likelihood function is used as a basis for hypothesis testing, which provides a means for evaluating global motion hypotheses.

In hybrid video coding, motion vectors used for motion compensation constitute an important set of decisions. Cost functions for block motion estimation that take the smoothness of the resulting motion vector field into account, in addition to the motion compensated prediction error, have been proposed. Computationally simple derivatives of sum of absolute differences and sum of squared differences-based criteria are studied in this paper. Cost functions are based on Lagrangian rate-distortion formulation, and the basic question is how the Lagrangian multiplier involved should be selected. Assumptions behind these cost functions are discussed, and a new method is derived for determining the multiplier. Comparisons with other strategies are made with experiments. The results show that the selection of the multiplier is not critical.

Digital video is very sensitive to bit errors which are injected especially in wireless transmission. Because the effects of errors in encoded digital video differ from analog video, traditional signal distortion measures, like peak signal-to-noise ratio (PSNR), do not correlate perfectly with the subjective quality of the video. In this paper, a novel method which does not need reference information about the original video is presented. It is assumed that MPEG-4 with video packets is used, and that error concealment is done by replacing the erroneous areas from the previous frame. The results obtained with the method are in line with PSNR.

An algorithm for recovering 3-D camera motion from sequences of images is proposed. The algorithm has four stages. In the first stage, the motion vector field is segmented using an EM-based method. The resulting segments are compared and the coherent regions are merged in the second stage. The candidates for the background regions are determined and finally used for 3-D motion estimation in the last two stages. Unlike most of the other methods, this approach tolerates also non-rigid motion in the scene. The experiments performed show that in some cases more information or reasoning is needed for selecting plausible motion parameters from several hypotheses.

Some intensity independent color models are studied experimentally in the scope of visual tracking to introduce robustness to illumination changes. Also, a plain color background model to allow modest camera motion is presented. The background is represented as a Gaussian mixture in color space. The EM algorithm is applied to find the decomposition and minimum description length principle is proposed to determine the number of mixture components. A simple tracking algorithm is outlined and the achieved results are introduced.

We present a method for making accurate 3-D measurements from monocular image sequences. The process of determining camera motion is completely separated from 3-D structure estimation. The algorithm has two steps: elimination of rotations and estimation of the camera translation. Elimination of rotations is based on pre-calibration, and estimation of the camera translation is based on locating the focus of expansion from image disparities. The method proposed utilizes the total least squares estimation technique. By using the motion data, the 3-D coordinates of the measurement points can be solved linearly up to a scale factor. Due to the nonrecursive nature of the method, it provides a fast approach for processing long image sequences in an accurate manner.

In geometrical camera calibration the objective is to determine a set of camera parameters that describe the mapping between 3-D reference coordinates and 2-D image coordinates. Various methods for camera calibration can be found from the literature. However surprisingly little attention has been paid to the whole calibration procedure, i.e., control point extraction from images, model fitting, image correction, and errors originating in these stages. The main interest has been in model fitting, although the other stages are also important. In this paper we present a four-step calibration procedure that is an extension to the two-step method. There is an additional step to compensate for distortion caused by circular features, and a step for correcting the distorted image coordinates. The image correction is performed with an empirical inverse model that accurately compensates for radial and tangential distortions. Finally, a linear method for solving the parameters of the inverse model is presented.

A camera calibration procedure intended for a 3D measurement application is presented, paying attention to the various error sources. The error may be measurement noise that is random by nature, but it may also be systematic originating from the calibration target used, geometrical distortions and illumination. In order to obtain good calibration results, the systematic error sources should be eliminated or their effects compensated for. Then, the camera parameters can be determined by fitting the corrected measurements to the camera model which in our case is a combination of a pinhole camera and lens distortion models. We also notice that a more complete camera model is needed to explain all the error components.

The spectral stability of illumination is an important aspect in color machine vision. The physical properties of lamps may change the spectrum of the illumination with time. In this work we examine the robustness of different color spaces against spectrally varying illumination in industrial wood defect inspection, when the inspection system is not adapted to the variations of illumination. The spectral changes are accomplished by digitally transforming the color temperature of illumination of wood images. We conclude that the original RGB color space is the best color space under varying illumination, the XYZ and CIELuv spaces being also very promising. An interesting observation is that features from some of the color spaces perform worse than features obtained from grey-level images. However, the importance of color information is emphasized, since RGB gives better results than grey level even under strong spectral variation of illumination.

We present a straightforward technique for determining the 3-D locations of feature points using sequences of monocular image frames captured by a moving camera. The motion of the camera is estimated simultaneously. In practice, only the camera needs careful calibration. Based on experiments, the repeatability is currently about 1/3500 and accuracy 1/2500. This approach has potential for high speed, as hundreds of points may be measured from the same image sequence.

Automated grading of lumber is attractive for the sawmill industry. Achieving better accuracy of quality grading and control of quality variation in volume production easily improves the profit obtained from it. We describe a color vision based framework to grading softwood lumber. The proposed inspection principle is to recognize the sound wood regions early, as this reduces the computational requirements at later defect recognition stages. The recognition stages are ordered based on their estimated costs and implementational complexity. This is important because color increases the data volumes significantly over grey scale images. Finally, the description of the board and its defects is passed to the quality grader which assigns the class giving the best price for each board. In comparative tests, the computational solutions have turned out to be simpler than with grey level images, compensating for the higher cost of the color imaging system. The effects of changes in the spectrum of illumination have also been evaluated to identify robust color features and to produce the requirements for color calibration.

In this paper we describe the outlines of a color vision solution for grading softwood lumber The proposed inspection principle is to recognize the sound wood regions early as this reduces the computational requirements at later stages. This is important because color increases the data volumes significantly over grey scale images. The computational solutions have turned out to be simpler than with grey scale data, compensating for the cost of the more sophisticated imaging system.

The purpose has been to find solutions for reliable real-time monocular visual tracking and simultaneous environment modeling. The goal is to estimate the relative motion of a camera with respect to a rigid scene by tracking features such as corners and lines. In the beginning, the 3-D locations of the features are not known accurately, but during the tracking process the model errors are reduced through the integration of new observations. The focus is on modeling measurement uncertainties and selecting the features to be extracted from image frames. Experiments have been performed by using a bank of trackers, each of which calculates estimates for location and motion using measurements of a few features at a time.>

Pietikainen and Rosenfeld (1982) introduced a class of texture measures based on first-order statistics derived from edges in an image. the objective of this paper is to evaluate the performance of these measures and some new edge-based texture measures using two different types of data sets: images taken from the Brodatz album and images from a practical wood surface inspection problem. The results obtained for edge-based measures are compared to those obtained by popular second-order texture measures and tonal features. The role of the classifier on the performance is also studied by comparing the results obtained for three parametric classifiers and for a nonparametric k-nearest neighbor classifier. The results indicate that edge-based approaches are very promising for surface inspection problems, because they are relatively simple to compute and have performed very well in experiments.>