Abstract
To construct a safe and sound autonomous driving system, object detection is essential, and research on fusion of sensors is being actively conducted to increase the detection rate of objects in a dynamic environment in which safety must be secured. Recently, considerable performance improvements in object detection have been achieved with the advent of the convolutional neural network (CNN) structure. In particular, the YOLO (You Only Look Once) architecture, which is suitable for real-time object detection by simultaneously predicting and classifying bounding boxes of objects, is receiving great attention. However, securing the robustness of object detection systems in various environments still remains a challenge. In this paper, we propose a weighted mean-based adaptive object detection strategy that enhances detection performance through convergence of individual object detection results based on an RGB camera and a LiDAR (Light Detection and Ranging) for autonomous driving. The proposed system utilizes the YOLO framework to perform object detection independently based on image data and point cloud data (PCD). Each detection result is united to reduce the number of objects not detected at the decision level by the weighted mean scheme. To evaluate the performance of the proposed object detection system, tests on vehicles and pedestrians were carried out using the KITTI Benchmark Suite. Test results demonstrated that the proposed strategy can achieve detection performance with a higher mean average precision (mAP) for targeted objects than an RGB camera and is also robust against external environmental changes.
Highlights
Object detection is a fundamental field of computer vision and an essential component of autonomous driving (AD), which uses sensors to detect the driving environment
We propose an adaptive object detection system that can improve the detection performance by redefining the bounding box through the convergence with multiple sensor detection results even if detection performance of one sensor is degraded by external environmental factors
The number of training epochs was set to 8000 for each YOLO model, and the performance evaluation of object detection was conducted based on average precision (AP), which is a performance evaluation indicator based on the PASCAL VOC intersection of union (IOU) metric and undetected rate
Summary
Object detection is a fundamental field of computer vision and an essential component of autonomous driving (AD), which uses sensors to detect the driving environment. Three object detection models were trained in [14] based on image data, LiDAR reflectance, and distance information, and a method of object detection using a multi-layer perceptron (MLP) by extracting features from the detection results has been proposed. They implemented late-fusion by redefining reliability through the MLP learning process, which takes the bounding box and its reliability generated by each single object detection model, and targets the ground truth and the intersection of union (IOU) of the bounding box. Even if one YOLO model failed to detect an object, it was possible to reduce the undetected rate by weighting the detection result from the entire model
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
