Deep Neural Network Based Vehicle and Pedestrian Detection for Autonomous Driving: A Survey

Vehicle and pedestrian detection is one of the critical tasks in autonomous driving. Since heterogeneous techniques have been proposed, the selection of a detection system with an appropriate balance among detection accuracy, speed and memory consumption for a specific task has become very challenging. To deal with this issue and to provide guidance for model selection, this paper analyzes several mainstream object detection architectures, including Faster R-CNN, R-FCN, and SSD, along with several typical feature extractors, such as ResNet50, ResNet101, MobileNetV1, MobileNetV2, InceptionV2 and InceptionResNetV2. By conducting extensive experiments using the KITTI benchmark, which is a commonly used street dataset, we demonstrate that Faster R-CNN ResNet50 obtains the best average precision (AP) (58%) for vehicle and pedestrian detection, with a speed of 8. 6 FPS. Faster R-CNN InceptionV2 performs best for detecting cars and detecting pedestrians respectively (74. 5% and 47. 3%). ResNet101 consumes the highest memory (9907 MB) and has the largest number of parameters (64. 42 millions), and InceptionResNetV2 is the slowest model (3. 05 FPS). SSD MobileNetV2 is the fastest model (70 FPS), and SSD MobileNetV1 is the lightest model in terms of memory usage (875 MB), both of which are suitable for applications on mobile and embedded devices.