Accurate ethnicity identification is essential for improving fairness, robustness, and cross-cultural understanding in real-world intelligent systems. Although recent models have advanced, they still lack the ability to dynamically adjust attention to facial regions when partial occlusions are present, limiting their effectiveness. This study introduces an Occlusion-Aware Attention Model (OAAM) designed to enhance robustness in ethnicity classification from facial images, even under diverse occlusion conditions. The proposed model builds upon a ResNet-34 backbone by integrating four Occlusion-Aware Attention Modules (OAAM) to suppress occluded features. In addition, we introduce a Regional Compensation Module (RCM) to recover features discarded due to occlusion. Finally, we use a Multi-Granularity Fusion (MGF) block to aggregate unoccluded facial features from all previous modules across different scales. We evaluate our model on the FairFace and the UTKFace benchmark datasets, which we augment by adding synthetic occlusion to existing ones to support a comprehensive ablation study. Experimental results show that our model achieves superior classification accuracy across most ethnicities, both within and across datasets. Furthermore, we conduct an extensive study on the impact of occluding distinct facial regions.

Gait is a commonly used biometric for human recognition. Its main advantage relies on its ability to identify people at distances at which other biometrics fail. In this paper, we develop a new approach for gait recognition that combines the distance transform with curvatures of local contours. We call our gait feature template the normal distance map. Our method encodes both body shapes and boundary curvatures into a novel feature descriptor that is more robust than existing gait representations. We evaluate our approach on the widely used and challenging USF and CASIA-B datasets. Furthermore, we evaluate it on the OU-ISIR gait dataset, the largest one available in the literature, to obtain statistically reliable results. We verify our approach is significantly superior to the current state-of-the-art under most conditions.

We study a two-player pursuit-evasion game, in which an agent moving amongst obstacles is to be maintained within ``sight" of a pursuing robot. Using a discretization of the environment, our main contribution is to design an efficient algorithm that decides, given initial positions of both pursuer and evader, if the evader can take any moving strategy to go out of sight of the pursuer at any time instant. If that happens, we say that the evader wins the game. We analyze the algorithm, present several optimizations and show results for different environments. For situations where the evader cannot win, we compute, in addition, a pursuit strategy that keeps the evader within sight, for every strategy the evader can take. Finally, if it is determined that the evader wins, we compute its optimal escape trajectory and the corresponding optimal pursuit trajectory.

Multiple cameras are used to track targets moving amongst obstacles. Surveillance video streamed from a top-view camera is processed to control the orientation of multiple pan-tilt-zoom cameras to cover as many targets as possible at high resolutions. The problem of maximizing the number of covered targets with a set of cameras has been shown to be computationally expensive and hence, several approximations have been suggested in the literature. We develop our own ones, compare them to some existing approaches by extensive simulation and show their superiority. Our new heuristics make an attempt at continuous panning that is needed when moving to real world experimentation to achieve seamless target tracking.

We consider the problem of tracking multiple agents moving amongst obstacles, using multiple cameras. Given an environment with obstacles, and many people moving through it, we construct a separate narrow field of view video for as many people as possible, by stitching together video segments from multiple cameras over time. We employ a novel approach to assign cameras to people as a function of time, with camera switches when needed. The problem is modeled as a bipartite graph and the solution corresponds to a maximum matching. As people move, the solution is efficiently updated by computing an augmenting path rather than by solving for a new matching. This reduces computation time by an order of magnitude. In addition, solving for the shortest augmenting path minimizes the number of camera switches at each update. When not all people can be covered by the available cameras, we cluster as many people as possible into small groups, then assign cameras to groups using a minimum cost matching algorithm. We test our method using numerous runs from different simulators.

We consider the problem of cropping surveillance videos. This process chooses a trajectory that a small sub-window can take through the video, selecting the most important parts of the video for display on a smaller monitor. We model the information content of the video simply, by whether the image changes at each pixel. Then we show that we can find the globally optimal trajectory for a cropping window by using a shortest path algorithm. In practice, we can speed up this process without affecting the results, by stitching together trajectories computed over short intervals. This also reduces system latency. We then show that we can use a second shortest path formulation to find good cuts from one trajectory to another, improving coverage of interesting events in the video. We describe additional techniques to improve the quality and efficiency of the algorithm, and show results on surveillance videos.