Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentation
This addresses the need for efficient multi-task perception systems in autonomous driving, though it appears incremental as it builds on existing multi-task learning approaches.
The paper tackles the problem of real-time visual perception for autonomous driving by introducing DSPNet, a shared convolutional architecture that simultaneously performs object detection, depth estimation, and semantic segmentation from a single image. The model achieves 14.0 fps on a GTX 1080 with 1024x512 input while using less than 850 MiB GPU memory, improving both precision and efficiency over single-task combinations.
As the demand for enabling high-level autonomous driving has increased in recent years and visual perception is one of the critical features to enable fully autonomous driving, in this paper, we introduce an efficient approach for simultaneous object detection, depth estimation and pixel-level semantic segmentation using a shared convolutional architecture. The proposed network model, which we named Driving Scene Perception Network (DSPNet), uses multi-level feature maps and multi-task learning to improve the accuracy and efficiency of object detection, depth estimation and image segmentation tasks from a single input image. Hence, the resulting network model uses less than 850 MiB of GPU memory and achieves 14.0 fps on NVIDIA GeForce GTX 1080 with a 1024x512 input image, and both precision and efficiency have been improved over combination of single tasks.