.png){kind=icon}
返回
TS-BEV: BEV object detection algorithm based on temporal-spatial feature fusion
.png){kind=icon}
PRE
AI
DOI：10.1016/j.displa.2024.102814.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In order to accurately identify occluding targets and infer the motion state of objects, we propose a Bird's-Eye View Object Detection Network based on Temporal-Spatial feature fusion (TS-BEV), which replaces the previous multi-frame sampling method by using the cyclic propagation mode of historical frame instance information. We design a new Temporal-Spatial feature fusion attention module, which fully integrates temporal information and spatial features, and improves the inference and training speed. In response to realize multi-frame feature fusion across multiple scales and views, we propose an efficient Temporal-Spatial deformable aggregation module, which performs feature sampling and weighted summation from multiple feature maps of historical frames and current frames, and makes full use of the parallel computing capabilities of GPUs and AI chips to further improve efficiency. Furthermore, in order to solve the lack of global inference in the context of temporal-spatial fusion BEV features and the inability of instance features distributed in different locations to fully interact, we further design the BEV self-attention mechanism module to perform global operation of features, enhance global inference ability and fully interact with instance features. We have carried out extensive experimental experiments on the challenging BEV object detection nuScenes dataset, quantitative results show that our method achieves excellent performance of 61.5% mAP and 68.5% NDS in camera-only 3D object detection tasks, and qualitative results show that TS-BEV can effectively solve the problem of 3D object detection in complex traffic background with lack of light at night, with good robustness and scalability.
Keyword:
BEV object detection
Temporal-Spatial feature fusion
Temporal-Spatial deformable aggregation
BEV self-attention
期刊
IF:
3.4
论文数:
2.3K
被引数:
3.2K
机构
引用论文
R-VPCG: RGB image feature fusion-based virtual point cloud generation for 3D car detectionR-vpcg: 基于RGB图像特征融合的三维汽车检测虚拟点云生成.png)
DISPLAYS
DISPLAYSIF3.4
PREAI
分享收藏DAGL-Faster: Domain adaptive faster r-cnn for vehicle object detection in rainy and foggy weather conditionsDISPLAYS
DISPLAYSIF3.4
PREAI
分享收藏Pressure-Based Bioassay Perceived by a Flexible Pressure Sensor with Synergistic Enhancement of the Photothermal Effect通过具有协同增强光热效应的柔性压力传感器感知的基于压力的生物测定
PREAI
分享收藏Myelination Defects and Neuronal Hyperexcitability in the Neocortex of Connexin 32-deficient Mice
PREAI
分享收藏
Hydrothermal preparation and low temperature magnetic properties of TbOOH, DyOOH, HoOOH, ErOOH, and YbOOHTbOOH，DyOOH，HoOOH，ErOOH和YbOOH的水热制备和低温磁性
PREAI
分享收藏
查看更多内容