Monocular 3D Detection With Geometric Constraint Embedding and Semi-Supervised Training

Li, Peixuan; Zhao, Huaici

doi:10.1109/lra.2021.3061343

Cited by 59 publications

(44 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these experiments, we show the contribution of each proposed component to the overall performance of the monocular 3D object detection task. We follow the default setup of Li (2020) to train the baseline model. We use the 40 recall positions Average Precision (AP| R40 ) metric to evaluate the following experimental results for a fair comparison with the official KITTI benchmark.…”

Section: Ablation Study Accumulated Impact Of Our Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution

Bui

Ngo

Pham

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Monocular 3D object detection has recently become prevalent in autonomous driving and navigation applications due to its cost-efficiency and easy-to-embed to existent vehicles. The most challenging task in monocular vision is to estimate a reliable object’s location cause of the lack of depth information in RGB images. Many methods tackle this ill-posed problem by directly regressing the object’s depth or take the depth map as a supplement input to enhance the model’s results. However, the performance relies heavily on the estimated depth map quality, which is bias to the training data. In this work, we propose depth-adaptive convolution to replace the traditional 2D convolution to deal with the divergent context of the image’s features. This lead to significant improvement in both training convergence and testing accuracy. Second, we propose a ground plane model that utilizes geometric constraints in the pose estimation process. With the new method, named GAC3D, we achieve better detection results. We demonstrate our approach on the KITTI 3D Object Detection benchmark, which outperforms existing monocular methods.

show abstract

Section: Ablation Study Accumulated Impact Of Our Proposed Methodsmentioning

confidence: 99%

“…The system of Eq. ( 17) is the baseline transformation in Li (2020). The over-determined system of linear equations AP = b is solved by using the ordinary least square method.…”

Section: D-3d Transformationmentioning

confidence: 99%

GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution

Bui

Ngo

Pham

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…This concise design causes the outstanding work to become the first real-time algorithm for the monocular 3D object detection task. Subsequently, KM3D [18] adopts a differentiable geometric reasoning module to realize the end-to-end training. Admittedly, the success of these methods is inspiring, but they all ignore the possible errors in the intermediate process due to a long detection pipeline, which has a bad effect on the detection performance.…”

Section: Methodsmentioning

confidence: 99%

“…For the 2D task, these components mainly include a heatmap, 2D size, and 2D center offset, but the 3D task usually contains a keypoints heatmap, keypoints offset, local orientation, 3D dimension and 3D object confidence. Based on the predicted 3D properties, we follow the practice of [18] and adopt a geometric reasoning module (GRM) to solve the 3D position for objects. Furthermore, we design an uncertainty prediction module for characterizing the errors in the detection pipeline to optimize the 3D object position.…”

Section: Methodsmentioning

confidence: 99%

Monocular 3D Object Detection Based on Uncertainty Prediction of Keypoints

Zhao

Liu

2021

Machines

Self Cite

View full text Add to dashboard Cite

Three-dimensional (3D) object detection is an important task in the field of machine vision, in which the detection of 3D objects using monocular vision is even more challenging. We observe that most of the existing monocular methods focus on the design of the feature extraction framework or embedded geometric constraints, but ignore the possible errors in the intermediate process of the detection pipeline. These errors may be further amplified in the subsequent processes. After exploring the existing detection framework of keypoints, we find that the accuracy of keypoints prediction will seriously affect the solution of 3D object position. Therefore, we propose a novel keypoints uncertainty prediction network (KUP-Net) for monocular 3D object detection. In this work, we design an uncertainty prediction module to characterize the uncertainty that exists in keypoint prediction. Then, the uncertainty is used for joint optimization with object position. In addition, we adopt position-encoding to assist the uncertainty prediction, and use a timing coefficient to optimize the learning process. The experiments on our detector are conducted on the KITTI benchmark. For the two levels of easy and moderate, we achieve accuracy of 17.26 and 11.78 in AP3D, and achieve accuracy of 23.59 and 16.63 in APBEV, which are higher than the latest method KM3D.

show abstract

“…The 3D detection can be divided into two groups by the type of data: LiDAR and image-based methods (Y. Wang et al, 2018;P. Li et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Real-Time Semantic Slam With DCNN-Based Feature Point Detection, Matching and Dense Point Cloud Aggregation

Vishnyakov

Sgibnev

Sheverdin

et al. 2021

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. In this paper we present the semantic SLAM method based on a bundle of deep convolutional neural networks. It provides real-time dense semantic scene reconstruction for the autonomous driving system of an off-road robotic vehicle. Most state-of-the-art neural networks require large computing resources that go beyond the capabilities of many robotic platforms. We propose an architecture for 3D semantic scene reconstruction on top of the recent progress in computer vision by integrating SuperPoint, SuperGlue, Bi3D, DeepLabV3+, RTM3D and additional module with pre-processing, inference and postprocessing operations performed on GPU. We also updated our simulated dataset for semantic segmentation and added disparity images.

show abstract

Monocular 3D Detection With Geometric Constraint Embedding and Semi-Supervised Training

Cited by 59 publications

References 28 publications

GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution

GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution

Monocular 3D Object Detection Based on Uncertainty Prediction of Keypoints

Real-Time Semantic Slam With DCNN-Based Feature Point Detection, Matching and Dense Point Cloud Aggregation

Contact Info

Product

Resources

About