Deformable-Heatmap-Segmentation for Automobile Visual Perception

2024/07/10 by Hongyu Jin, Jin, Hongyu
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing and 3D Reconstruction #Industrial Vision Systems and Defect Detection #Manufacturing Process and Optimization

paper · pdf · doi:10.48550/arxiv.2407.07493

openalex publication_date 2024/07/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Semantic segmentation of road elements in 2D images is a crucial task in the recognition of some static objects such as lane lines and free space. In this paper, we propose DHSNet,which extracts the objects features with a end-to-end architecture along with a heatmap proposal. Deformable convolutions are also utilized in the proposed network. The DHSNet finely combines low-level feature maps with high-level ones by using upsampling operators as well as downsampling operators in a U-shape manner. Besides, DHSNet also aims to capture static objects of various shapes and scales. We also predict a proposal heatmap to detect the proposal points for more accurate target aiming in the network.

Related

• Semantic Segmentation for Real-World and Synthetic Vehicle's Forward-Facing Camera Images
• Semantic Segmentation With Multi Scale Spatial Attention For Self\n Driving Cars
• In Defense of Pre-trained ImageNet Architectures for Real-time Semantic\n Segmentation of Road-driving Images
• Detecting Lane and Road Markings at A Distance with Perspective\n Transformer Layers
• Detection and Retrieval of Out-of-Distribution Objects in Semantic\n Segmentation