Generic object tracking (GOT) is one of the main topics in computer vision for many years. The goal of GOT is to recognize and locate a specific object in the form of bounding box throughout a sequence of images. Moreover, GOT also requires algorithms to locate objects down to instances level. These requirements produce some unique challenges especially for deep learning based GOT algorithms that may easily become over-fitting if given a really small training dataset of the object during the online tracking process. To deal with this issue, we propose a novel Reptile meta-tracking algorithm, which adopts a first-order meta-learning technique so that during initialization, the visual tracker only requires few training examples and few steps of optimization to perform well. The proposed Reptile meta-tracker is evaluated on OTB2015 and VOT2018 tracking benchmark datasets, and outperforms several state-of-the-art trackers using one-pass evaluation.

Traffic sign recognition is a very important function in automatic driving assistance systems (ADAS). This study addresses the design and implementation of a vision‐based ADAS based on an image‐based speed‐limit sign (SLS) recognition algorithm, which can automatically detect and recognise SLS on the road in real‐time. To improve the recognition rate of SLS having different orientations and scales in the image, this study also presents a new sign content description algorithm, which describes the detected road sign using centroid‐to‐contour (CtC) distances of the extracted sign content. The proposed CtC descriptor is robust to translation, rotation and scale changes of the SLS in the image. This advantage improves the recognition accuracy of a support vector machine classifier trained using a large database of traffic signs. The proposed SLS recognition method had been implemented on two different embedded platforms, each of them equipped with an ARM‐based Quad‐Core CPU running Android 4.4 operating system. Experimental results validate that the proposed method not only provides a high recognition rate, but also achieves real‐time performance up to 30 frames per second for processing 1280 × 720 video streams running on a commercial ARM‐based smartphone.

Image keypoint descriptor matching is an important pre‐processing task in various computer vision applications. This study first introduces an existing multi‐resolution exhaustive search (MRES) algorithm combined with a multi‐resolution candidate elimination technique to address this issue efficiently. A graphics processing unit (GPU) acceleration design is then proposed to improve its real‐time performance. Suppose that a scale‐invariant feature transform like algorithm is used to extract image keypoint descriptors of an input image, the MRES algorithm first computes a multi‐resolution table of each keypoint descriptor by using a L 1 ‐norm‐based dimension reduction approach. Next, a fast candidate elimination algorithm is employed based on the multi‐resolution tables to remove all non‐candidates from a candidate matching list by using a simple L 1 ‐norm computation. However, when the MRES algorithm was implemented on the central processing unit, the authors observed that the step of multi‐resolution table building is not computationally efficient, but it is very suitable for parallel implementation on the GPU. Therefore, this study presents a GPU acceleration method for the MRES algorithm to achieve better real‐time performance. Experimental results validate the computational efficiency and matching accuracy of the proposed algorithm by comparing with three existing methods.

This study presents a cost‐efficient and high‐performance field programmable gate array (FPGA)‐based hardware implementation of a contrast‐preserving image dynamic range compression algorithm, which is an important function used in modern digital video cameras and displays to improve visual quality of standard dynamic range colour images (8 bits/channel). To achieve this purpose, a hardware‐friendly approximation to an existing fast dynamic range compression with local contrast preservation (FDRCLCP) algorithm is proposed. The computation of the proposed approximated FDRCLCP algorithm requires only fixed‐point unsigned binary addition, multiplication, and bit‐shifting. Moreover, the proposed hardware implementation uses a line buffer instead of a frame buffer to process whole image data. These advantages significantly improve throughput performance and reduce memory requirement of the system. The FPGA implementation of the proposed algorithm requires only about 98 K bits on‐chip memory and achieves about 170.24 MHz operating frequency by using an Altera Cyclone II device. This is a large improvement compared with the existing results as it is quick enough to process full high‐definition videos (1920 × 1080 pixels) at least 80 frames per second using a low‐cost FPGA device.

This study addresses low dynamic range (LDR) image/video enhancement for digital video cameras. A new fast dynamic range compression format with a local-contrast-preservation (FDRCLCP) algorithm resolves this problem efficiently. The proposed FDRCLCP algorithm can combine with any continuously differentiable intensity transfer function to achieve LDR image enhancement. In combination with the FDRCLCP algorithm, a new intensity-transfer function is proposed, adaptively accomplishing dynamic range compression and edge-contrast enhancement depending on the local mean value of the input luminance image. The proposed method also extends to a linear color remapping approach, not only preserving the original image's color information, but also controlling color saturation of the resulting image. Moreover, a look-up-table (LUT) acceleration approach improves the processing speed of the proposed FDRCLCP algorithm in processing video signals, allowing real-time video enhancement processing. Experimental results show that the proposed method not only provides good visual representation in both quantitative and visual comparisons, but also achieves real-time performance for video processing.

This paper presents a novel simultaneous dynamic range compression and local contrast enhancement algorithm, termed as SDALA, to resolve low dynamic range (LDR) image enhancement problem. The proposed SDALA is able to combine with any differentiable intensity transfer function, which greatly increases the applicability of the proposed method. Moreover, the proposed method can separately control the level of enhancement on the overall lightness and contrast achieved at the output. Experimental results validate the performance of the proposed method by comparing with two existent methods, both quantitatively and visually.

This paper presents a novel design of visual state estimation for an image-based tracking control system to estimate system state during visual tracking control process. The advantage of this design is that it can estimate the target status and target image velocity without using the knowledge of target’s 3D motion-model information. This advantage is helpful for real-time visual tracking controller design. In order to increase the robustness against random observation noise, a neural network based self-tuning algorithm is proposed using echo state network (ESN) technique. The visual state estimator is designed by combining a Kalman filter with the ESN-based self-tuning algorithm. The performance of this estimator design has been evaluated using computer simulation. Several interesting experiments on a mobile robot validate the proposed algorithms.

This paper presents a novel heterogeneity-projection hard-decision (HPHD) color interpolation procedure for reproduction of Bayer mosaic images. The proposed algorithm aims to estimate the optimal interpolation direction and perform hard-decision interpolation, in which each pixel only needs to be interpolated once. A new heterogeneity-projection scheme based on a novel spectral-spatial correlation concept is proposed to estimate the best interpolation direction directly from the original mosaic image. Using the proposed heterogeneity-projection scheme, a hard-decision rule can be decided before performing the interpolation. The advantage of this scheme is that it provides an efficient way for decision-based algorithms to generate improved results using fewer computations. Compared with three recently reported demosaicing techniques, Gunturk's, Lu's, and Li's methods, the proposed HPHD outperforms all of them in both PSNR values and S-CIELAB deltaEab measures by utilizing 25 natural images from Kodak PhotoCD.

This paper presents a real-time human-robot interface system (HRIS), which processes both speech and vision information to improve the quality of communication between human and an autonomous mobile robot. The HRIS contains a real-time speech attention system and a real-time face tracking system. In the speech attention system, a microphone-array voice acquisition system has been developed to estimate the direction of speaker and purify the speaker's speech signal in a noisy environment. The developed face tracking system aims to track the speaker's face under illumination variation and react to the face motion. The proposed HRIS can provide a robot with the abilities of finding a speaker's direction, tracking the speaker's face, moving its body to the speaker, focusing its attention to the speaker who is talking to it, and purifying the speaker's speech. The experimental results show that the HRIS not only purifies speech signal with a significant performance, but also tracks a face under illumination variation in real-time

This paper presents a novel face tracking control scheme for human-robot interaction control in image plane. This control scheme is robust to the velocity quantization error in practical implementation. A visual tracking controller is designed for ensuring global asymptotic stability of the closed-loop visual tracking system based on an error-state control model in image plane. In order to overcome the quantization uncertainty encountered in practical systems, an image-based robust control law is proposed to guarantee the stability of the robotic control system based on Lyapunov theory. This design provides a useful solution for smooth visual tracking control of slow-motion robots in a home setting. Simulation and experimental results verify the effectiveness of the proposed visual tracking control scheme, both in terms of tracking performance and system convergence

This paper studies the general parking problem for unicycle-modeled mobile robots by combining the motion planning method with tracking controller design. We add a re-designed virtual trajectory to the original trajectory such that the parking problem can be transformed into a tracking problem. Consequently, a new global tracking controller is proposed to achieve the locally exponential convergence. Further improvement of the tracking performance is achieved using linearization and pole placement method. The proposed controllers are quite simple and can be easily implemented. The effectiveness of the proposed method is validated by several interesting experiments including the parallel parking and the back-into-garage parking.