PersDet: Monocular 3D Detection in Perspective Bird's-Eye-View
Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to other 3D detectors for autonomous driving and robotics. However, transforming image features into BEV necessitates special operators to conduct feature sampling. These operators are not supported on many edge devices, bringing extra obstacles when deploying detectors. To address this problem, we revisit the generation of BEV representation and propose detecting objects in perspective BEV -- a new BEV representation that does not require feature sampling. We demonstrate that perspective BEV features can likewise enjoy the benefits of the BEV paradigm. Moreover, the perspective BEV improves detection performance by addressing issues caused by feature sampling. We propose PersDet for high-performance object detection in perspective BEV space based on this discovery. While implementing a simple and memory-efficient structure, PersDet outperforms existing state-of-the-art monocular methods on the nuScenes benchmark, reaching 34.6% mAP and 40.8% NDS when using ResNet-50 as the backbone.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous Drivingobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography
This paper proposes a method to extract the position and pose of vehicles in the 3D world from a single traffic camera. Most previous monocular 3D vehicle detection algorithms focused on cameras on vehicles from the pers…
vehicle detectionBEV-MODNet: Monocular Camera based Bird's Eye View Moving Object Detection for Autonomous Driving
Detection of moving objects is a very important task in autonomous driving systems. After the perception phase, motion planning is typically performed in Bird's Eye View (BEV) space. This would require projection of obje…
Autonomous DrivingMotion PlanningMotion SegmentationMoving Object Detection+4BirdSLAM: Monocular Multibody SLAM in Bird's-Eye View
In this paper, we present BirdSLAM, a novel simultaneous localization and mapping (SLAM) system for the challenging scenario of autonomous driving platforms equipped with only a monocular camera. BirdSLAM tackles challen…
Autonomous DrivingMonocular ReconstructionObject LocalizationSimultaneous Localization and MappingM3D-RPN: Monocular 3D Region Proposal Network for Object Detection
Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algori…
3D Object Detection3D Object Detection From Monocular ImagesAutonomous DrivingMonocular 3D Object Detection+5Focus on BEV: Self-calibrated Cycle View Transformation for Monocular Birds-Eye-View Segmentation
Birds-Eye-View (BEV) segmentation aims to establish a spatial mapping from the perspective view to the top view and estimate the semantic maps from monocular images. Recent studies have encountered difficulties in view t…
BEV Segmentation