Range Adaptation for 3D Object Detection in LiDAR

Wang, Ze; Ding, Sihao; Liu, Ying; Zhao, Minming; Roychowdhury, Sohini; Wallin, Andreas; Sapiro, Guillermo; Qiu, Qiang

doi:10.1109/iccvw.2019.00285

Cited by 36 publications

(20 citation statements)

References 20 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meyer used a fully convolutional network to predict a multimodal distribution over 3D boxes for each point, and then it efficiently fused these distributions to generate a prediction for each object [ 26 ]. Wang introduced domain adaption in migration learning to achieve cross-range adaptation and achieved better performance in the detection task for long-range objects [ 27 ].…”

Section: Related Workmentioning

confidence: 99%

Spatial Attention Frustum: A 3D Object Detection Method Focusing on Occluded Objects

Zhang

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

Achieving the accurate perception of occluded objects for autonomous vehicles is a challenging problem. Human vision can always quickly locate important object regions in complex external scenes, while other regions are only roughly analysed or ignored, defined as the visual attention mechanism. However, the perception system of autonomous vehicles cannot know which part of the point cloud is in the region of interest. Therefore, it is meaningful to explore how to use the visual attention mechanism in the perception system of autonomous driving. In this paper, we propose the model of the spatial attention frustum to solve object occlusion in 3D object detection. The spatial attention frustum can suppress unimportant features and allocate limited neural computing resources to critical parts of the scene, thereby providing greater relevance and easier processing for higher-level perceptual reasoning tasks. To ensure that our method maintains good reasoning ability when faced with occluded objects with only a partial structure, we propose a local feature aggregation module to capture more complex local features of the point cloud. Finally, we discuss the projection constraint relationship between the 3D bounding box and the 2D bounding box and propose a joint anchor box projection loss function, which will help to improve the overall performance of our method. The results of the KITTI dataset show that our proposed method can effectively improve the detection accuracy of occluded objects. Our method achieves 89.46%, 79.91% and 75.53% detection accuracy in the easy, moderate, and hard difficulty levels of the car category, and achieves a 6.97% performance improvement especially in the hard category with a high degree of occlusion. Our one-stage method does not need to rely on another refining stage, comparable to the accuracy of the two-stage method.

show abstract

Section: Related Workmentioning

confidence: 99%

Spatial Attention Frustum: A 3D Object Detection Method Focusing on Occluded Objects

Zhang

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…LiDARNet [38] follows this discriminator approach, which was previously applied to camera images in [68]. The same principle of minimizing domain gaps by employing a discriminator is applied in [58]. Here, the authors conduct the model adaptation on intermediate layers of the DNN to improve the detection of far range objects.…”

Section: Domain-invariant Feature Learningmentioning

confidence: 99%

A Survey on Deep Domain Adaptation for LiDAR Perception

Triess

Mariella

Rist

et al. 2021

2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)

View full text Add to dashboard Cite

Scalable systems for automated driving have to reliably cope with an open-world setting. This means, the perception systems are exposed to drastic domain shifts, like changes in weather conditions, time-dependent aspects, or geographic regions. Covering all domains with annotated data is impossible because of the endless variations of domains and the time-consuming and expensive annotation process. Furthermore, fast development cycles of the system additionally introduce hardware changes, such as sensor types and vehicle setups, and the required knowledge transfer from simulation.To enable scalable automated driving, it is therefore crucial to address these domain shifts in a robust and efficient manner. Over the last years, a vast amount of different domain adaptation techniques evolved. There already exists a number of survey papers for domain adaptation on camera images, however, a survey for LiDAR perception is absent. Nevertheless, LiDAR is a vital sensor for automated driving that provides detailed 3D scans of the vehicle's surroundings. To stimulate future research, this paper presents a comprehensive review of recent progress in domain adaptation methods and formulates interesting research questions specifically targeted towards LiDAR perception.

show abstract

“…However, they considered point clouds of isolated objects, which are very different from the ones captured in driving scenes. Others approaches project 3D points to the frontal or bird's-eye view (BEV) and apply UDA techniques in the resulting 2D images for object detection or semantic segmentation [48], [49], [50], which may be sub-optimal in terms of models' accuracy.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection

You

Diaz-Ruiz

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Self-driving cars must detect other vehicles and pedestrians in 3D to plan safe routes and avoid collisions. State-of-the-art 3D object detectors, based on deep learning, have shown promising accuracy but are prone to over-fit to domain idiosyncrasies, making them fail in new environmentsa serious problem if autonomous vehicles are meant to operate freely. In this paper, we propose a novel learning approach that drastically reduces this gap by fine-tuning the detector on pseudo-labels in the target domain, which our method generates while the vehicle is parked, based on replays of previously recorded driving sequences. In these replays, objects are tracked over time, and detections are interpolated and extrapolated-crucially, leveraging future information to catch hard cases. We show, on five autonomous driving datasets, that fine-tuning the object detector on these pseudo-labels substantially reduces the domain gap to new driving environments, yielding drastic improvements in accuracy and detection reliability.

show abstract

Range Adaptation for 3D Object Detection in LiDAR

Cited by 36 publications

References 20 publications

Spatial Attention Frustum: A 3D Object Detection Method Focusing on Occluded Objects

Spatial Attention Frustum: A 3D Object Detection Method Focusing on Occluded Objects

A Survey on Deep Domain Adaptation for LiDAR Perception

Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection

Contact Info

Product

Resources

About