YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception
This addresses real-time autonomous driving systems with limited computation resources, but it is incremental as it builds on existing multi-tasking approaches.
The paper tackles panoptic driving perception by proposing a multi-task learning network for traffic object detection, drivable road area segmentation, and lane detection, achieving new state-of-the-art accuracy and speed on the BDD100K dataset with inference time reduced by half.
Over the last decade, multi-tasking learning approaches have achieved promising results in solving panoptic driving perception problems, providing both high-precision and high-efficiency performance. It has become a popular paradigm when designing networks for real-time practical autonomous driving system, where computation resources are limited. This paper proposed an effective and efficient multi-task learning network to simultaneously perform the task of traffic object detection, drivable road area segmentation and lane detection. Our model achieved the new state-of-the-art (SOTA) performance in terms of accuracy and speed on the challenging BDD100K dataset. Especially, the inference time is reduced by half compared to the previous SOTA model. Code will be released in the near future.