Search

Most object detection methods use rectangular bounding boxes to represent the object, while the representative points network (RepPoints) employs a point set to describe the object. The RepPoints can provide more fine-grained localization and facilitates classification. However, it ignores the difference between localization and classification tasks. Therefore, a lightweight RepPoints with decoupling of the sampling point set (LRP-DS) is proposed in this paper. Firstly, the lightweight MobileNet-V2 and Feature Pyramid Networks (FPN) is employed as the backbone network to realize the lightweight network, rather than the Resnet. Secondly, considering the difference between classification and localization tasks, the sampling points of classification and localization are decoupled, by introducing classification free sampling method. Finally, due to the introduction of the classification free sampling method, the problem of the mismatch between the localization accuracy and the classification confidence is highlighted, so the localization score is employed to describe the localization accuracy independently. The final network structure of this paper achieves 73.3% mean average precision (mAP) on the VOC07 test dataset, which is 1.9% higher than original RepPoints with the same backbone network MobileNetV2 and FPN. Our LRP-DS has a detection speed of 20FPS for the input image of (1000, 600), on RTX2060 GPU, which is nearly twice as fast as the backbone network of ResNet50 and FPN. Experimental results show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

At present, light curtain is a widely-used method to measure the vehicle profile size. However, it is sensitive to temperature, humidity, dust and other weather factors. In this paper, a lidar-based system with a K-frame-based algorithm is proposed for measuring vehicle profile size. The system is composed of left lidar, right lidar, front lidar, control box and industry controlling computer. Within the system, a K-frame-based methodology is investigated, which include several probable algorithm combinations. Three groups of experiments are conducted. An optimal algorithm combination, A16, is determined through the first group experiments. In the second group experiments, various types of vehicles are chosen to verify the generality and repeatability of the proposed system and methodology. The third group experiments are implemented to compare with vision-based methods and other lidar-based methods. The experimental results show that the proposed K-frame-based methodology is far more accurate than the comparative methods. [ABSTRACT FROM AUTHOR]