Center-based 3D Object Detection and Tracking

Yin, Tianwei

doi:10.48550/arxiv.2006.11275

Cited by 50 publications

(132 citation statements)

References 45 publications

Supporting

Mentioning

132

Contrasting

Order By: Relevance

“…SECOND [38] improves the voxel feature learning process by introducing 3D sparse convolutions. CenterPoints [42] proposes a center-based assignment that can be applied on feature maps for accurate location prediction. Pillar-based approaches generally transform point clouds into Bird-Eye-View (BEV) pillars and apply 2D CNNs for 3D object detection.…”

Section: Related Workmentioning

confidence: 99%

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Mao¹,

Niu²,

Bai³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a flexible and high-performance framework, named Pyramid R-CNN, for two-stage 3D object detection from point clouds. Current approaches generally rely on the points or voxels of interest for RoI feature extraction on the second stage, but cannot effectively handle the sparsity and non-uniform distribution of those points, and this may result in failures in detecting objects that are far away.To resolve the problems, we propose a novel second-stage module, named pyramid RoI head, to adaptively learn the features from the sparse points of interest. The pyramid RoI head consists of three key components. Firstly, we propose the RoI-grid Pyramid, which mitigates the sparsity problem by extensively collecting points of interest for each RoI in a pyramid manner. Secondly, we propose RoI-grid Attention, a new operation that can encode richer information from sparse points by incorporating conventional attentionbased and graph-based point operators into a unified formulation. Thirdly, we propose the Density-Aware Radius Prediction (DARP) module, which can adapt to different point density levels by dynamically adjusting the focusing range of RoIs. Combining the three components, our pyramid RoI head is robust to the sparse and imbalanced circumstances, and can be applied upon various 3D backbones to consistently boost the detection performance. Extensive experiments show that Pyramid R-CNN outperforms the state-of-the-art 3D detection models by a large margin on both the KITTI dataset and the Waymo Open dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Mao¹,

Niu²,

Bai³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Configuration Details: In this experiment, the backbone task f is a CenterPoint LiDAR detector [41] for both vehicles and pedestrians, trained on the simulated data from Carla in addition to proprietary real-world data. The downstream planner g is a modified version of the BasicAgent included in the Carla Python API, where changes were made to improve the performance of the planner.…”

Section: Carla Leaderboard Evaluationmentioning

confidence: 99%

“…• We perform extensive large-scale experiments demonstrating the efficacy of our approach using Carla [8] simulator for driving tasks. We create surrogate models of two well-known LiDAR detectors, PIXOR [40] and Centerpoint [41], as our backbone task. • We show that our approach is closest to the backbone task compared to the baselines evaluated on several metrics, and yields a 20 times reduction in compute time.…”

Section: Introductionmentioning

confidence: 99%

A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation

Sadeghi¹,

Rogers²,

Gunn³

et al. 2021

Preprint

View full text Add to dashboard Cite

There has been increasing interest in characterising the error behaviour of systems which contain deep learning models before deploying them into any safety-critical scenario. However, characterising such behaviour usually requires large-scale testing of the model that can be extremely computationally expensive for complex real-world tasks. For example, tasks involving compute intensive object detectors as one of their components. In this work, we propose an approach that enables efficient large-scale testing using simplified low-fidelity simulators and without the computational cost of executing expensive deep learning models. Our approach relies on designing an efficient surrogate model corresponding to the compute intensive components of the task under test. We demonstrate the efficacy of our methodology by evaluating the performance of an autonomous driving task in the Carla [8] simulator with reduced computational expense by training efficient surrogate models for PIXOR [40] and CenterPoint [41] LiDAR detectors, whilst demonstrating that the accuracy of the simulation is maintained.Preprint. Under review.

show abstract

“…We use a dense, single-stage convolutional header for detecting objects using the per-cell features. Similarly to [4,43], we first predict if a cell contains the center of an object for some class. For each center cell, we then predict an associated bounding box and use non-maximum suppression to remove duplicates.…”

Section: Output Predictionmentioning

confidence: 99%

MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data

Laddha¹,

Gautam²,

Palombo³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this work, we propose MVFuseNet, a novel end-toend method for joint object detection and motion forecasting from a temporal sequence of LiDAR data. Most existing methods operate in a single view by projecting data in either range view (RV) or bird's eye view (BEV). In contrast, we propose a method that effectively utilizes both RV and BEV for spatio-temporal feature learning as part of a temporal fusion network as well as for multi-scale feature learning in the backbone network. Further, we propose a novel sequential fusion approach that effectively utilizes multiple views in the temporal fusion network. We show the benefits of our multi-view approach for the tasks of detection and motion forecasting on two large-scale self-driving data sets, achieving state-of-the-art results. Furthermore, we show that MVFusenet scales well to large operating ranges while maintaining real-time performance.

show abstract

Center-based 3D Object Detection and Tracking

Cited by 50 publications

References 45 publications

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation

MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data

Contact Info

Product

Resources

About