Abstract
3D Object detection is a critical mission of the perception system of a self-driving vehicle. Existing bounding box-based methods are hard to train due to the need to remove duplicated detections in the post-processing stage. In this paper, we propose a center point-based deep neural network (DNN) architecture named RCBi-CenterNet that predicts the absolute pose for each detected object in the 3D world space. RCBi-CenterNet is composed of a recursive composite network with a dual-backbone feature extractor and a bi-directional feature pyramid network (BiFPN) for cross-scale feature fusion. In the detection head, we predict a confidence heatmap that is used to determine the position of detected objects. The other pose information, including depth and orientation, is regressed. We conducted extensive experiments on the Peking University/Baidu-Autonomous Driving dataset, which contains more than 60,000 labeled 3D vehicle instances from 5277 real-world images, and each vehicle object is annotated with the absolute pose described by the six degrees of freedom (6DOF). We validated the design choices of various data augmentation methods and the backbone options. Through an ablation study and an overall comparison with the state-of-the-art (SOTA), namely CenterNet, we showed that the proposed RCBi-CenterNet presents performance gains of 2.16%, 2.76%, and 5.24% in Top 1, Top 3, and Top 10 mean average precision (mAP). The model and the result could serve as a credible benchmark for future research in center point-based object detection.
Highlights
Object detection is at the heart of numerous computer vision applications such as face detection [1], video surveillance [2], optical character recognition [3], object counting/tracking [4,5], etc
Unlike traditional bounding box-based object detection tasks, which use the Intersection over Union (IoU) thresholds to determine true/false positives, this task utilizes the mean average precision between the predicted and ground truth pose information as the evaluation metric
The novelty and efficiency of CenterNet drive us to explore its application in autonomous driving
Summary
Object detection is at the heart of numerous computer vision applications such as face detection [1], video surveillance [2], optical character recognition [3], object counting/tracking [4,5], etc. In autonomous driving [6], the core mission of the perception system of a vehicle computer is to detect nearby objects in real-time and make the optimal driving decisions such as path planning and collision avoidance. Self-driving cars have been in the spotlight and gained explosive development during the past decade [7]. Several recent accidents of autonomous vehicles are caused by object misclassification or not being recognized [8]. Increasing the object detection capability of a self-driving system is one of the highest priorities
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.
