Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving

About

In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted from 2D images, our method solves this problem in the reconstructed 3D space in order to exploit 3D contexts explicitly. To this end, we first leverage a stand-alone module to transform the input data from 2D image plane to 3D point clouds space for a better input representation, then we perform the 3D detection using PointNet backbone net to obtain objects 3D locations, dimensions and orientations. To enhance the discriminative capability of point clouds, we propose a multi-modal feature fusion module to embed the complementary RGB cue into the generated point clouds representation. We argue that it is more effective to infer the 3D bounding boxes from the generated 3D scene space (i.e., X,Y, Z space) compared to the image plane (i.e., R,G,B image plane). Evaluation on the challenging KITTI dataset shows that our approach boosts the performance of state-of-the-art monocular approach by a large margin.

Xinzhu Ma, Zhihui Wang, Haojie Li, Pengbo Zhang, Xin Fan, Wanli Ouyang• 2019

Related benchmarks

TaskDatasetResultRank
3D Object DetectionKITTI car (test)
AP3D (Easy)16.5
195
Bird's Eye View DetectionKITTI Car class official (test)
AP (Easy)25.03
62
3D Object DetectionKITTI car (val)--
62
3D Object DetectionKITTI (test)
AP_3D Car (Easy)16.5
60
Bird's Eye View Object Detection (Car)KITTI (test)
APBEV (Easy) @IoU=0.725.03
59
Bird's eye view object detectionKITTI (test)
APBEV@0.7 (Easy)25.03
53
Bird's Eye View (BEV) DetectionKITTI Cars (IoU3D ≥ 0.7) (test)
APBEV R40 (Easy)25.03
52
3D Object DetectionKITTI cars (val)
AP Easy32.23
48
3D Object Detection (Cars)KITTI (test)
AP (Easy)16.5
40
3D Object DetectionKITTI (test)
AP Car (IoU=0.7) Easy16.5
38
Showing 10 of 43 rows

Other info

Follow for update