Stereo R-CNN Based 3D Object Detection for Autonomous Driving

Li, Peiliang; Chen, Xiaozhi; Shen, Shaojie

doi:10.1109/cvpr.2019.00783

Cited by 550 publications

(395 citation statements)

References 32 publications

Supporting

Mentioning

365

Contrasting

Order By: Relevance

“…3DOP [5] exploits stereo images and prior knowledge about the scene to directly reason in 3D. Stereo R-CNN [16] tackles 3D object detection by exploiting stereo imagery and produces stereo boxes, keypoints, dimensions and viewpoint angles, summarized in a learned 3D box estimation module. In MV3D [6], a sensorfusion approach for LIDAR and RGB images is presented, approaching 3D object proposal generation and multi-view feature fusion via individual sub-networks.…”

Section: Related Workmentioning

confidence: 99%

Disentangling Monocular 3D Object Detection

Simonelli

Bulò²,

Porzi³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

464

308

View full text Add to dashboard Cite

Figure 1: Results obtained from our single image, monocular 3D object detection network MonoDIS on a KITTI3D test image with corresponding birds-eye view, showing its ability to estimate size and orientation of objects at different scales. AbstractIn this paper we propose an approach for monocular 3D object detection from a single RGB image, which leverages a novel disentangling transformation for 2D and 3D detection losses and a novel, self-supervised confidence score for 3D bounding boxes. Our proposed loss disentanglement has the twofold advantage of simplifying the training dynamics in the presence of losses with complex interactions of parameters, and sidestepping the issue of balancing independent regression terms. Our solution overcomes these issues by isolating the contribution made by groups of parameters to a given loss, without changing its nature. We further apply loss disentanglement to another novel, signed Intersection-over-Union criterion-driven loss for improving 2D detection results. Besides our methodological innovations, we critically review the AP metric used in KITTI3D, which emerged as the most important dataset for comparing 3D detection results. We identify and resolve a flaw in the 11-point interpolated AP metric, affecting all previously published detection results and particularly biases the results of monocular 3D detection. We provide extensive experimental evaluations and ablation studies on the KITTI3D and nuScenes datasets, setting new state-of-theart results on object category car by large margins.

show abstract

Section: Related Workmentioning

confidence: 99%

Disentangling Monocular 3D Object Detection

Simonelli

Bulò²,

Porzi³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

464

308

View full text Add to dashboard Cite

show abstract

“…We compare our approach with state-of-the-art methods [2], [6], [12], [13], [15], [16], [31], which are divided into two groups depending on the input (i.e., point clouds or camera images). One group consists of MonoPSR [31] (Mono-based) and Stereo R-CNN [6] (Stereo-based) which process camera images with RGB information. The other group includes MV3D (LiDAR) [2], BirdNet [12], RT3D [13], VeloFCN [15] and LMNet [16] which are based on point clouds only.…”

Section: B Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…3D object detection [1]- [6] has proved to be increasingly important in many fields, such as autonomous driving [7], mobile robots [8] and virtual/augmented reality [9]. While there have been remarkable progresses in the field of image-based 2D object detection, 3D object detection is far less explored than its 2D counterpart.…”

Section: Introductionmentioning

confidence: 99%

FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds

Zhou

Tan

Shao

et al. 2019

2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

View full text Add to dashboard Cite

3D object detection from raw and sparse point clouds has been far less treated to date, compared with its 2D counterpart. In this paper, we propose a novel framework called FVNet for 3D front-view proposal generation and object detection from point clouds. It consists of two stages: generation of front-view proposals and estimation of 3D bounding box parameters. Instead of generating proposals from camera images or bird's-eye-view maps, we first project point clouds onto a cylindrical surface to generate front-view feature maps which retains rich information. We then introduce a proposal generation network to predict 3D region proposals from the generated maps and further extrude objects of interest from the whole point cloud. Finally, we present another network to extract the point-wise features from the extruded object points and regress the final 3D bounding box parameters in the canonical coordinates. Our framework achieves real-time performance with 12ms per point cloud sample. Extensive experiments on the 3D detection benchmark KITTI show that the proposed architecture outperforms state-of-the-art techniques which take either camera images or point clouds as input, in terms of accuracy and inference time.

show abstract

“…Each frame in 3D points cloud data is processed in the same way, and one common key step in the process is to generate feature maps from points cloud data. Due to the popularity of CNN based solutions to object detection for autonomous driving vehicles [4,15,25], in this paper, we focus on the feature maps generated by the convolutional layers in CNN networks.…”

Section: Towards Feature Based Fusion Of Vehicle Data 21 Convolutionmentioning

confidence: 99%

Cooper: Cooperative Perception for Connected Autonomous Vehicles Based on 3D Point Clouds

Chen

Tang

Yang

et al. 2019

2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS)

249

242

View full text Add to dashboard Cite

Autonomous vehicles are heavily reliant upon their sensors to perfect the perception of surrounding environments, however, with the current state of technology, the data which a vehicle uses is confined to that from its own sensors. Data sharing between vehicles and/or edge servers is limited by the available network bandwidth and the stringent real-time constraints of autonomous driving applications. To address these issues, we propose a point cloud feature based cooperative perception framework (F-Cooper) for connected autonomous vehicles to achieve a better object detection precision. Not only will feature based data be sufficient for the training process, we also use the features' intrinsically small size to achieve real-time edge computing, without running the risk of congesting the network. Our experiment results show that by fusing features, we are able to achieve a better object detection result, around 10% improvement for detection within 20 meters and 30% for further distances, as well as achieve faster edge computing with a low communication delay, requiring 71 milliseconds in certain feature selections. To the best of our knowledge, we are the first to introduce feature-level data fusion to connected autonomous vehicles for the purpose of enhancing object detection and making realtime edge computing on inter-vehicle data feasible for autonomous vehicles.

show abstract

Stereo R-CNN Based 3D Object Detection for Autonomous Driving

Cited by 550 publications

References 32 publications

Disentangling Monocular 3D Object Detection

Disentangling Monocular 3D Object Detection

FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds

Cooper: Cooperative Perception for Connected Autonomous Vehicles Based on 3D Point Clouds

Contact Info

Product

Resources

About