Quad-pol Synthetic Aperture Radar (SAR) images consist of four polarization schemes(HH, HV, VH, and VV), each having different responses from different types of terrain, foliage, and buildings. These polarimetric SAR images show correlations between cross-polarizations (HV and VH) and co-polarizations (HH and VV). Real-time transmission or storage of these large raw SAR images from UAVs in hostile electromagnetic environments becomes impractical due to file size, bandwidth constraints, and limited bit rate. To overcome this challenge, we propose a Distributed Polarimetric SAR Compression and Deblocking network (DPCD) that can exploit polarimetric correlations to improve compression efficiency. Our approach enables distributed and independent encoding of quad-pol SAR images while utilizing a learning-based method for joint frequency and spatial domain deblocking of the primary polarization, integrating feature-level information from Side Information (SI). Experimental results on the NGA SAR dataset show that DPCD outperforms state-of-the-art single-polarization compression techniques, particularly at lower bitrates, delivering significant bitrate savings without compromising image quality.

View transformation is crucial for gait recognition. Most existing methods use a view transformation models (VTM) or generative models (VAE or GAN) to achieve transformation. These approaches commonly adopt a paradigm of transforming a gait feature from one view to another. However, most existing methods attempt to use a single or multiple, large-view transformation model to directly transform a source view image to the target view image. Such transformations usually suffer from precision problems under large viewpoint variations due to the lack of fine view prediction. To overcome this challenge, we introduce a novel framework, ViewDiffGait, employing a view pyramid structure and diffusion models. ViewDiffGait is formulated as an iterative refinement generation task in a biologically interpretable way, capable of generating more accurate lateral view images from coarse to fine. Unlike the typical diffusion model that directly adds and removes Gaussian noise in the original image, the ViewDiffGait diffusion process involves a view pyramid structure to capture fine view transformations. The diffusion process adds view noise from the pyramid top to the bottom, while the denoising process removes view noise from the pyramid bottom to the top. We conducted extensive experiments on the CASIA-B and OUMVLP datasets, demonstrating that ViewDiffGait can generate more realistic images, remove variations effectively, and lead to high performance in real applications.

In recent years, event cameras have achieved significant attention due to their advantages over conventional cameras. Event cameras have high dynamic range, no motion blur, and high temporal resolution. Contrary to traditional cameras which generate intensity frames, event cameras output a stream of asynchronous events based on brightness change. There is extensive ongoing research on performing computer vision tasks like object detection, classification, etc via the event camera. However, due to the unconventional output format of the event camera, it is difficult to perform computer vision tasks directly on the event stream. Mostly, works reconstruct the intensity image from the event stream and then perform such tasks. An important and crucial task is feature detection and description. Scale-invariant feature transform (SIFT) is a widely-used scale-invariant keypoint detector and descriptor that is invariant to transformations like scale, rotation, noise, and illumination. In this work, given an event voxel, we directly generate the LoG pyramid for SIFT keypoint detection. We fit a 3rd-degree polynomial and calculate the polynomial roots to compute the scale-space extrema response for SIFT keypoint detection. Since the extrema computation is performed after LoG thresholding, the solution is computationally less expensive. Experimental results validate the effectiveness of our system.

Object detection is a widely researched topic in computer vision; however, current models often struggle with processing degraded images with adverse imaging conditions like low light, blur, and haze. Conventional approaches involve a separate image recovery network prior to detection, resulting in a large network that is sub-optimal in performance. Alternatively, in this study, we propose a lightweight plug-and-play solution to improve the performance of object detectors on degraded images, without the need for retraining the vision task, i.e., detector network. This solution utilizes an image enhancement plug-in subnetwork that can be turned on and off for the main vision task network, leading to improved detection accuracy without sacrificing inference time. Empirically, our proposed model achieved a 48.9% mean average precision (mAP) on a degraded Pascal VOC dataset, compared to the baseline model at 26.7%.

Colorization of Near-Infrared (NIR) image is a challenging problem due to the lack of low-level clues available in the luminance channel of visible images. Recently, deep learning has witnessed remarkable progress in the NIR image colorization approaches. However, we have observed that most research focuses on designing deeper and wider architectures to improve the quality of RGB images at the expense of computational burden and speed. Few studies have adopted lightweight but effective modules to improve the efficiency of NIR image colorization without affecting its performance. In this paper, we propose the Discrete Cosine Transform (DCT)-based Residual Network (DCT-RCAN) for NIR image colorization. Specifically, the output of our network is four coefficients generated by the Two-Dimensional (2D) 4×4 DCT of RGB images, which reduces the training difficulty of our network by explicitly separating low-frequency and high-frequency details into four subgroups. We adopt the Residual in Residual (RIR) module as a basic module in our network, which can reduce the complexity of the model. Thus, our method can focus on more crucial underlying patterns in channel dimension in a lightweight manner. Extensive experiments validate that our DCT-RCAN is computationally efficient and demonstrate competitive results against state-of-the-art NIR image colorization methods.

With the development of airplane platforms, aerial image classification plays an important role in a wide range of remote sensing applications. The number of most of aerial image dataset is very limited compared with other computer vision datasets. Unlike many works that use data augmentation to solve this problem, we adopt a novel strategy, called, label splitting, to deal with limited samples. Specifically, each sample has its original semantic label, we assign a new appearance label via unsupervised clustering for each sample by label splitting. Then an optimized triplet loss learning is applied to distill domain specific knowledge. This is achieved through a binary tree forest partitioning and triplets selection and optimization scheme that controls the triplet quality. Simulation results on NWPU, UCM and AID datasets demonstrate that proposed solution achieves the state-of-the-art performance in the aerial image classification.

In visual object recognition problems essential to surveillance and navigation problems in a variety of military and civilian use cases, low-resolution and low-quality images present great challenges to this problem. Recent advancements in deep learning based methods like EDSR/VDSR have boosted pixel domain image super-resolution (SR) performances significantly in terms of signal to noise ratio(SNR)/ mean square error(MSE) metrics of the super-resolved image. However, these pixel domain signal quality metrics may not directly correlate to the machine vision tasks like key points detection and object recognition. In this work, we develop a machine vision tasks-friendly super-resolution technique which enhances the gradient images and associated features from the low-resolution images that benefit the high level machine vision tasks. Here, a residual learning deep neural network based gradient image super-resolution solution is developed with scale space adaptive network depth, and simulation results demonstrate the performance gains in both gradient image quality as well as key points repeatability.

Compared with a single platform, cooperative autonomous unmanned aerial vehicles (UAVs) offer efficiency and robustness in performing complex tasks. Focusing on ground mobile targets that intermittently emit radio frequency signals, this paper presents a decentralized control architecture for multiple UAVs, equipped only with rudimentary sensors, to search, detect, and locate targets over large areas. The proposed architecture has in its core a decision logic which governs the state of operation for each UAV based on sensor readings and communicated data. To support the findings, extensive simulation results are presented, focusing primarily on two success measures that the UAVs seek to minimize: overall time to search for a group of targets and the final target localization error achieved. The results of the simulations have provided support for hardware flight tests.

In this paper, we present a control architecture that allows multiple Unmanned Aerial Vehicles (UAVs) to cooperatively detect mobile RF (Radio Frequency) emitting ground targets. The architecture is developed under the premise that UAVs are controlled as a distributed system. The distributed system-based technique maximizes the search and detection capabilities of multiple UAVs. We use a hybrid approach that combines a set of intentional cooperative rules with emerging properties of a swarm to accomplish the objective. The UAVs are equipped only with low-precision RF direction finding sensors and we assume the targets may emit signals randomly with variable duration. Once a target is detected, each UAV optimizes a cost function to determine whether to participate in a cooperative localization task. The cost function balances between the completion of detecting all targets (global search) in the search space and increasing the precision of cooperatively locating already detected targets. A search function for each UAV determines the collective search patterns of collaborating UAVs. Two functions used by each UAV determine (1) the optimal number of UAVs involved in locating targets, (2) the search pattern to detect all targets, and (3) the UAV flight path for an individual UAV. We show the validity of our algorithm using simulation results. Hardware implementation of the strategies is planned for this coming year.

We describe the design of an anthropomorphic robot head intended as a research platform for studying autonomously learning active vision systems. The robot head closely mimics the major degrees of freedom of the human neck/eye apparatus and allows a number of facial expressions. We show that our robot head can shift its direction of gaze at speeds which come close to that of human saccades. Since our design only makes use of low cost consumer grade components, it paves the way for widespread use of anthropomorphic robot heads in science, education, health-care, and entertainment.