Ego-motion estimation and moving object tracking using multi-layer LIDAR

Miyasaka, Takeo; Ohama, Yoshihiro; Ninomiya, Yoshiki

doi:10.1109/ivs.2009.5164269

Cited by 52 publications

(28 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The hybrid approach uses the best of both paradigms; it incorporates raw data into the map representation and so does not require geometric models, and estimates the map in a recursive manner without the need to store the scan history. In [38], the first step of mouvement estimation is achieved by ICP algorithm between two successive scans from a 4 layers lidar. The obtained parameters are then used as initialization of a step of local map association with the last scan, as in [39].…”

Section: Related Workmentioning

confidence: 99%

Virtual 3D City Model for Navigation in Urban Areas

Cappelle

Najjar

Charpillet

et al. 2011

J Intell Robot Syst

View full text Add to dashboard Cite

vient d'etre acceptéInternational audienceIn this paper, we propose to study the integration of a new source of a priori information, which is the virtual 3D city model. We study this integration for two tasks: vehicles geo-localization and obstacles detection. A virtual 3D city model is a realistic representation of the evolution environment of a vehicle. It is a database of geographical and textured 3D data. We describe an ego-localization method that combines measurements of a GPS (Global Positioning System) receiver, odometers, a gyrometer, a video camera and a virtual 3D city model. GPS is often consider as the main sensor for localization of vehicles. But, in urban areas, GPS is not precise or even can be unavailable. So, GPS data are fused with odometers and gyrometer measurements using an Unscented Kalman Filter (UKF). However, during long GPS unavailability, localization with only odometers and gyrometer drift. Thus, we propose a new observation of the location of the vehicle. This observation is based on the matching between the current image acquired by an on-board camera and the virtual 3D city model of the environment. We also propose an obstacle detection method based on the comparison between the image acquired by the on-board camera and the image extracted from the 3D model. The following principle is used: the image acquired by the on-board camera contains the possible dynamic obstacles whereas they are absent from the 3D model. The two proposed concepts are tested on real data

show abstract

Section: Related Workmentioning

confidence: 99%

Virtual 3D City Model for Navigation in Urban Areas

Cappelle

Najjar

Charpillet

et al. 2011

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…移動ロボットやビークル自らが周囲環境をセンシングして移動物体を追跡（位置や速度，大きさを推定）するシステムの構築は，様々な分野で必要不可欠な技術である．そのため，車載レーザスキャナやカメラ，ミリ波レーダを用いた移動物体追跡システムが提案され，実用化されている (Cho et al,2014, Fayad and Cherfaoui, 2007, Mertz et al, 2013, Mukhtar et al, 2015, Wang et al, 2015．複数の移動ロボットが近接する場合，通信系を介して各ロボットのセンサ情報を共有することで，移動物体が 1台のロボットの視野外や死角に存在しても他のロボットから観測できるため，移動物体追跡の精度や信頼性が向上する (Ahmad and Lima, 2013, Robin and Lacroix, 2016, Tsokas and Kyriakopoulos, 2012, Wang and Gu, 2012 , Hashimoto et al, 2014, Tamura et al, 2016．近年，マルチレイヤレーザスキャナの普及により，それを利用した環境認識の研究が盛んである (Miyata et al, 2009, Zeng, 2013 …”

Section: 緒言unclassified

Cooperative tracking of moving objects with multiple mobile robots using in-vehicle laser scanner in GNSS-denied environments

Kanaki

Hashimoto

Yoden

et al. 2017

Transactions of the JSME (In Japanese)

View full text Add to dashboard Cite

This paper presents a laser-based tracking (estimation of pose and size) of moving objects using multiple mobile robots in Global-navigation-satellite-system (GNSS)-denied environments. Each robot is equipped with a multilayer laser scanner and detects moving objects, such as people, cars, and bicycles, in its own laser-scanned images by applying an occupancy-gridbased method. It then sends measurement information related to the moving objects to a central server. The central server estimates the objects' poses (positions and velocities) and sizes from the measurement information using Bayesian filter. In this cooperative-tracking method, the nearby robots always share their tracking information, allowing tracking of invisible or partially visible objects. To perform a reliable cooperative tracking, robots have to correctly identify their relative pose. To do so in GNSS-denied environments, the relative pose is estimated by scan matching using laser measurements captured by both sensor nodes. Such cooperative scan matching is performed by 4-points-congruent-sets (4PCS)-matching-based coarse registration and Iterative-closest-point (ICP)-based fine registration methods. The experimental results of tracking a car, a motorcycle, and a pedestrian with two robots in an outdoor GNSS-denied environment validate the proposed method.

show abstract

“…In addition, other clusters generated by LIDAR-based detection are also tracked, and moving vehicles can be detected based on size and velocity [21]. These results are integrated to eliminate false positives because many false positives occur around the lamps and wheel housings of cars in the vision-based detection.…”

Section: Integration and Trackingmentioning

confidence: 99%

Reliable pedestrian recognition combining high-definition LIDAR and vision data

Kidono

Naito

Miura

2012

2012 15th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

Pedestrian recognition is one of the key technologies for advanced driver assistance systems and autonomous driving systems. The present paper proposes a fusion system for reliable pedestrian recognition using high-definition LIDAR and a vision sensor to achieve high performance under various conditions. Pedestrian candidates are extracted from two sensors in parallel by support vector machine-based classifiers. In particular, the region of interest in the image processing is set based on information about objects derived from the LIDAR processing in order to reduce false positives as well as the computational burden. All candidates are integrated by their likelihood, as calculated from their classification scores, using multiple thresholds according to the detection condition of the target in two sensors. A quantitative evaluation in a road environment confirms the effectiveness of the proposed system.

show abstract

Ego-motion estimation and moving object tracking using multi-layer LIDAR

Cited by 52 publications

References 6 publications

Virtual 3D City Model for Navigation in Urban Areas

Virtual 3D City Model for Navigation in Urban Areas

Cooperative tracking of moving objects with multiple mobile robots using in-vehicle laser scanner in GNSS-denied environments

Reliable pedestrian recognition combining high-definition LIDAR and vision data

Contact Info

Product

Resources

About