A Continuous Occlusion Model for Road Scene Understanding

Dhiman, Vikas; Tran, Quoc-Huy; Corso, Jason J.; Chandraker, Manmohan

doi:10.1109/cvpr.2016.469

Cited by 30 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[31,32] introduces a detailed geometry representation of objects using 3D wireframe models. To incorporate temporal information, some work [6,21] combine structure from motion and ground estimation to lift 2D detection boxes to 3D bounding boxes. Image-based methods usually rely on accurate depth estimation or landmark detection.…”

Section: Related Workmentioning

confidence: 99%

Multi-view 3D Object Detection Network for Autonomous Driving

Chen

Wan

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

2,811

1,897

View full text Add to dashboard Cite

This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes. We encode the sparse 3D point cloud with a compact multi-view representation. The network is composed of two subnetworks: one for 3D object proposal generation and another for multi-view feature fusion. The proposal network generates 3D candidate boxes efficiently from the bird's eye view representation of 3D point cloud. We design a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths. Experiments on the challenging KITTI benchmark show that our approach outperforms the state-of-the-art by around 25% and 30% AP on the tasks of 3D localization and 3D detection. In addition, for 2D detection, our approach obtains 10.3% higher AP than the state-of-the-art on the hard data among the LIDAR-based methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-view 3D Object Detection Network for Autonomous Driving

Chen

Wan

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

2,811

1,897

View full text Add to dashboard Cite

show abstract

“…BirdNet [8], MV3D [4], to novel object representations such as the work on 3DVP [9]. Some works also utilize other modalities along with 3D, such as corresponding 2D images [4] and structure from motion [12]. Among the neural network based approaches, many competitive approaches follow the success of 2D object detection methods and are based on 3D proposal networks and classifying them, e.g.…”

Section: Related Workmentioning

confidence: 99%

Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehicles

Srivastava

Jurie

Sharma

2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

We address the problem of 3D object detection from 2D monocular images in autonomous driving scenarios. We propose to lift the 2D images to 3D representations using learned neural networks and leverage existing networks working directly on 3D data to perform 3D object detection and localization. We show that, with carefully designed training mechanism and automatically selected minimally noisy data, such a method is not only feasible, but gives higher results than many methods working on actual 3D inputs acquired from physical sensors. On the challenging KITTI benchmark, we show that our 2D to 3D lifted method outperforms many recent competitive 3D networks while significantly outperforming previous state-of-the-art for 3D detection from monocular images. We also show that a late fusion of the output of the network trained on generated 3D images, with that trained on real 3D images, improves performance. We find the results very interesting and argue that such a method could serve as a highly reliable backup in case of malfunction of expensive 3D sensors, if not potentially making them redundant, at least in the case of low human injury risk autonomous navigation scenarios like warehouse automation.

show abstract

“…At the second layer, the previous hidden state of the second layer h (2) t−1 and the current hidden state of the first layer h (1) t are as the input of the three gates. Both the previous states (h…”

Section: Image Local Feature Representationmentioning

confidence: 99%

“…Here we use the attention mechanism as introduced in [29] for local feature. At each time-step, the attention mechanism uses the previous hidden state h (2) t−1 to decide the local feature. The attention model is defined as follows:…”

Section: Attention Mechanism For Local Image Featurementioning

confidence: 99%