Motion-based detection and tracking in 3D LiDAR scans

Dewan, Ayush; Caselitz, Tim; Tipaldi, Gian Diego; Burgard, Wolfram

doi:10.1109/icra.2016.7487649

Cited by 154 publications

(101 citation statements)

References 13 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…We attempt to minimize complexity through early-fusion architecture as we focus on real-time architecture for autonomous driving. However it is found that early-fusion architecture only (RGB x rgbFlow) is not capable of extracting the required features compared to Mid-Fusion which is consistent with other literature such as [27,4]. Thus we continue our experiments using Mid or Hybrid fusion.…”

Section: Resultssupporting

confidence: 82%

“…Motion Segmentation using LiDAR sensor: Most of LiDAR-based methods that have been used for motion segmentation problem were based on clustering methods such as [4] which predicts the points motion by methods such as RANSAC, and then clustering takes place for object-level perception. Vaquero et al [34] initially clustered vehicles points and then performed motion segmentation on the objects after matching the objects through sequential frames.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FuseMODNet: Real-Time Camera and LiDAR Based Moving Object Detection for Robust Low-Light Autonomous Driving

Rashed

Ramzy

Vaquero

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Moving object detection is a critical task for autonomous vehicles. As dynamic objects represent higher collision risk than static ones, our own ego-trajectories have to be planned attending to the future states of the moving elements of the scene. Motion can be perceived using temporal information such as optical flow. Conventional optical flow computation is based on camera sensors only, which makes it prone to failure in conditions with low illumination. On the other hand, LiDAR sensors are independent of illumination, as they measure the time-of-flight of their own emitted lasers. In this work, we propose a robust and real-time CNN architecture for Moving Object Detection (MOD) under low-light conditions by capturing motion information from both camera and LiDAR sensors. We demonstrate the impact of our algorithm on KITTI dataset where we simulate a low-light environment creating a novel dataset "Dark-KITTI". We obtain a 10.1% relative improvement on Dark-KITTI, and a 4.25% improvement on standard KITTI relative to our baselines. The proposed algorithm runs at 18 fps on a standard desktop GPU using 256 × 1224 resolution images.

show abstract

Section: Resultssupporting

confidence: 82%

Section: Related Workmentioning

confidence: 99%

FuseMODNet: Real-Time Camera and LiDAR Based Moving Object Detection for Robust Low-Light Autonomous Driving

Rashed

Ramzy

Vaquero

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

show abstract

“…When dealing with lidar detections a tracking system is necessary in order to provide the driving direction of the objects (e.g. [20]). Here, we can reduce the input to detections on the vehicles p = (x, y) and the driving direction as orientation vector o derived from the velocity.…”

Section: A Preprocessingmentioning

confidence: 99%

Anytime Lane-Level Intersection Estimation Based on Trajectories of Other Traffic Participants

Meyer

Walter

Lauer

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Estimating and understanding the current scene is an inevitable capability of automated vehicles. Usually, maps are used as prior for interpreting sensor measurements in order to drive safely and comfortably. Only few approaches take into account that maps might be outdated and lead to wrong assumptions on the environment. This work estimates a lanelevel intersection topology without any map prior by observing the trajectories of other traffic participants.We are able to deliver both a coarse lane-level topology as well as the lane course inside and outside of the intersection using Markov chain Monte Carlo sampling. The model is neither limited to a number of lanes or arms nor to the topology of the intersection.We present our results on an evaluation set of 1000 simulated intersections and achieve 99.9% accuracy on the topology estimation that takes only 36ms, when utilizing tracked object detections. The precise lane course on these intersections is estimated with an error of 15cm on average after 140ms. Our approach shows a similar level of precision on 14 realworld intersections with 18cm average deviation on simple intersections and 27cm for more complex scenarios. Here the estimation takes only 113ms in total.

show abstract

“…In 3D object detection and tracking, recent works include [18], [19]. In [18], a model-free object detection scheme based on convexity segmentation is used with a Kalman filter and constant velocity motion model.…”

Section: B Object Trackingmentioning

confidence: 99%

aUToTrack: A Lightweight Object Detection and Tracking System for the SAE AutoDrive Challenge

Burnett

Samavi

Waslander

et al. 2019

2019 16th Conference on Computer and Robot Vision (CRV)

View full text Add to dashboard Cite

The University of Toronto is one of eight teams competing in the SAE AutoDrive Challenge -a competition to develop a self-driving car by 2020. After placing first at the Year 1 challenge [1], we are headed to MCity in June 2019 for the second challenge. There, we will interact with pedestrians, cyclists, and cars. For safe operation, it is critical to have an accurate estimate of the position of all objects surrounding the vehicle. The contributions of this work are twofold: First, we present a new object detection and tracking dataset (UofTPed50), which uses GPS to ground truth the position and velocity of a pedestrian. To our knowledge, a dataset of this type for pedestrians has not been shown in the literature before. Second, we present a lightweight object detection and tracking system (aUToTrack) that uses vision, LIDAR, and GPS/IMU positioning to achieve state-of-theart performance on the KITTI Object Tracking benchmark. We show that aUToTrack accurately estimates the position and velocity of pedestrians, in real-time, using CPUs only. aUToTrack has been tested in closed-loop experiments on a real self-driving car (seen in Figure 1), and we demonstrate its performance on our dataset.

show abstract

Motion-based detection and tracking in 3D LiDAR scans

Cited by 154 publications

References 13 publications

FuseMODNet: Real-Time Camera and LiDAR Based Moving Object Detection for Robust Low-Light Autonomous Driving

FuseMODNet: Real-Time Camera and LiDAR Based Moving Object Detection for Robust Low-Light Autonomous Driving

Anytime Lane-Level Intersection Estimation Based on Trajectories of Other Traffic Participants

aUToTrack: A Lightweight Object Detection and Tracking System for the SAE AutoDrive Challenge

Contact Info

Product

Resources

About