Field-programmable gate arrays (FPGAs) and graphics processing units (GPUs) are often used when real-time performance in video processing is required. An accelerated processor is chosen based on task-specific priorities (power consumption, processing time, and detection accuracy), and this decision is normally made once at design time. All three of the characteristics are important, particularly in battery-powered systems. Here, we propose a method for moving selection of processing platform from a single design-time choice to a continuous run-time one. We implement Histogram of Oriented Gradients (HOG) for cars and people and Mixture-of-Gaussians motion detectors running across FPGA, GPU, and central processing unit in a heterogeneous system. We use this to detect illegally parked vehicles in urban scenes. Power, time, and accuracy information for each detector is characterized. An anomaly measure is assigned to each detected object based on its trajectory and location compared with learned contextual movement patterns. This drives processor and implementation selection so that scenes with high behavioral anomalies are processed with faster but more power-hungry implementations, but routine or static time periods are processed with power-optimized and less accurate slower versions. Real-time performance is evaluated on video data sets including i-LIDS. Compared with power-optimized static selection, automatic dynamic implementation mapping is 10% more accurate, but draws 12-W of extra power in our testbed desktop system.
State-of-the-art pedestrian detectors are capable of finding humans in images with reasonable accuracy. However, accurate object detectors such as Integral Channel Features (ICF) do not provide good reliability; they are unable to identify detections which they are less confident (or more uncertain) about. We apply existing methods for generating probabilistic measures from classifier scores (such as Platt exponential scaling and Isotonic Regression) and compare these to Gaussian Process classifiers (GPCs), which can provide more informative predictive variance. GPCs are less accurate than ICF classifiers, but GPCs and Adaboost with Platt scaling both provide improved reliability over existing methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.