CenterNet: Keypoint Triplets for Object Detection

Duan, Kailiang; Bai, Song; Xie, Lingxi; Qi, Honggang; Huang, Qingming; Tian, Qi

doi:10.48550/arxiv.1904.08189

Cited by 54 publications

(39 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detection head is a final dense block of 5 layers and a growth parameter of 7. The detection head is inspired by CenterNet [16] and produces bird's eye view heat maps where local maxima are interpreted as objects. Non-maximum suppression is not necessary with this method so it is not used.…”

Section: Object Detectionmentioning

confidence: 99%

PixSet : An Opportunity for 3D Computer Vision to Go Beyond Point Clouds With a Full-Waveform LiDAR Dataset

Déziel¹,

Merriaux²,

Tremblay³

et al. 2021

Preprint

View full text Add to dashboard Cite

Leddar PixSet is a new publicly available dataset (dataset.leddartech.com) for autonomous driving research and development. One key novelty of this dataset is the presence of full-waveform data from the Leddar Pixell sensor, a solid-state flash LiDAR. Full-waveform data has been shown to improve the performance of perception algorithms in airborne applications but is yet to be demonstrated for terrestrial applications such as autonomous driving. The PixSet dataset contains approximately 29k frames from 97 sequences recorded in high-density urban areas, using a set of various sensors (cameras, LiDARs, radar, IMU, etc.) Each frame has been manually annotated with 3D bounding boxes.

show abstract

Section: Object Detectionmentioning

confidence: 99%

PixSet : An Opportunity for 3D Computer Vision to Go Beyond Point Clouds With a Full-Waveform LiDAR Dataset

Déziel¹,

Merriaux²,

Tremblay³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Our task of estimating people's "ground point" is similar to keypoints detection in computer vision [1,15], which has been extensively studied. Recently, CornerNet [13] and its variants CenterNet [6,31] achieve competing performance on object detection task. One essential component in these frameworks is the estimation of keypoints for candidate objects.…”

Section: Related Workmentioning

confidence: 99%

Real-time 3D Deep Multi-Camera Tracking

You,

Jiang

2020

Preprint

View full text Add to dashboard Cite

Tracking a crowd in 3D using multiple RGB cameras is a challenging task. Most previous multi-camera tracking algorithms are designed for offline setting and have high computational complexity. Robust real-time multi-camera 3D tracking is still an unsolved problem. In this work, we propose a novel end-to-end tracking pipeline, Deep Multi-Camera Tracking (DMCT), which achieves reliable real-time multi-camera people tracking. Our DMCT consists of 1) a fast and novel perspective-aware Deep GroudPoint Network, 2) a fusion procedure for groundplane occupancy heatmap estimation, 3) a novel Deep Glimpse Network for person detection and 4) a fast and accurate online tracker. Our design fully unleashes the power of deep neural network to estimate the "ground point" of each person in each color image, which can be optimized to run efficiently and robustly. Our fusion procedure, glimpse network and tracker merge the results from different views, find people candidates using multiple video frames and then track people on the fused heatmap. Our system achieves the state-of-the-art tracking results while maintaining real-time performance. Apart from evaluation on the challenging WILDTRACK dataset, we also collect two more tracking datasets with high-quality labels from two different environments and camera settings. Our experimental results confirm that our proposed real-time pipeline gives superior results to previous approaches.

show abstract

“…CornerNet [15] detects the two opposite corners of a bounding box and pairs them using an embedding. CenterNet [4] detects the center of the object and uses regression to determine the dimensions of the object.…”

Section: Object Detectionmentioning

confidence: 99%

“…Many published approaches rely on modified 2D object detectors. The authors of CenterNet object detector published [4] an evaluation of a slightly modified version of their detector on the KITTI dataset. Mousavian et al [20] use a 2D bounding box and regress orientation and dimensions of vehicles separately and combine them with geometry constraints to obtain a final 3D bounding box.…”

Section: Vehicle Detectionmentioning

confidence: 99%

Detection of 3D Bounding Boxes of Vehicles Using Perspective Transformation for Accurate Speed Measurement

Kocur,

Ftáčnik

2020

Preprint

View full text Add to dashboard Cite

Detection and tracking of vehicles captured by traffic surveillance cameras is a key component of intelligent transportation systems. We present an improved version of our algorithm for detection of 3D bounding boxes of vehicles, their tracking and subsequent speed estimation. Our algorithm utilizes the known geometry of vanishing points in the surveilled scene to construct a perspective transformation. The transformation enables an intuitive simplification of the problem of detecting 3D bounding boxes to detection of 2D bounding boxes with one additional parameter using a standard 2D object detector. Main contribution of this paper is an improved construction of the perspective transformation which is more robust and fully automatic and an extended experimental evaluation of speed estimation. We test our algorithm on the speed estimation task of the BrnoCompSpeed dataset. We evaluate our approach with different configurations to gauge the relationship between accuracy and computational costs and benefits of 3D bounding box detection over 2D detection. All of the tested configurations run in real-time and are fully automatic. Compared to other published state-of-the-art fully automatic results our algorithm reduces the mean absolute speed measurement error by 32% (1.10 km/h to 0.75 km/h) and the absolute median error by 40% (0.97 km/h to 0.58 km/h).

show abstract

CenterNet: Keypoint Triplets for Object Detection

Cited by 54 publications

References 38 publications

PixSet : An Opportunity for 3D Computer Vision to Go Beyond Point Clouds With a Full-Waveform LiDAR Dataset

PixSet : An Opportunity for 3D Computer Vision to Go Beyond Point Clouds With a Full-Waveform LiDAR Dataset

Real-time 3D Deep Multi-Camera Tracking

Detection of 3D Bounding Boxes of Vehicles Using Perspective Transformation for Accurate Speed Measurement

Contact Info

Product

Resources

About