GPU-based Pedestrian Detection for Autonomous Driving
This work addresses the need for efficient pedestrian detection in autonomous vehicles, but it is incremental as it applies standard methods to a new hardware platform.
The authors tackled real-time pedestrian detection for autonomous driving by implementing a pipeline of existing algorithms on an embedded GPU-CPU platform, achieving an 8x speedup and better performance per watt compared to desktop systems.
We propose a real-time pedestrian detection system for the embedded Nvidia Tegra X1 GPU-CPU hybrid platform. The pipeline is composed by the following state-of-the-art algorithms: Histogram of Local Binary Patterns (LBP) and Histograms of Oriented Gradients (HOG) features extracted from the input image; Pyramidal Sliding Window technique for candidate generation; and Support Vector Machine (SVM) for classification. Results show a 8x speedup in the target Tegra X1 platform and a better performance/watt ratio than desktop CUDA platforms in study.