Encoding images to 3D by sequential model with single target feature extractor

Abstract

Assisted driving is a necessary way to realize autonomous driving, in which bird's-eye-view (BEV) is an ideal solution to perceive the targets around the body, i.e., the information acquired by the sensors of the body is extracted and semantic features are integrated into the BEV plane for downstream tasks such as target detection, scene segmentation, and path planning, etc. BEV-based pure vision target detection refers to the use of ordinary cameras without relying on other sensors to perceive the targets around the body. BEV-based pure visual target detection, on the other hand, refers to the use of ordinary cameras to perceive targets around the body without relying on other sensors, and Lift Splat Shoot (LSS) is a more typical solution among the existing schemes. Since the information obtained by each camera in assisted driving is always continuous, incorporating the temporal information into the model can achieve better detection results. We design the model (Sequential and Single Target based LSS) SSTL, and the experiment proves that our model has a certain performance improvement based on the original model.