Fusion at detection level for frontal object perception

Chavéz-García, R. Omar; Vu, Trung; Aycard, Olivier

doi:10.1109/ivs.2014.6856555

Cited by 13 publications

(10 citation statements)

References 6 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It consists of finding the best vehicle tracks estimates (ω * ) according to a shape model (P(ω|z 1:t )), prior model (P(ω)) and likelihood model (P(z 1:t |ω)) (Equation 3). Afterwards, this method uses the pose estimate and the latest sensor measurements to update the grid [12].…”

Section: A Lidar Processingmentioning

confidence: 99%

“…2) LIDAR-based Detection: As described [1], [12], we focus on identifying the inconsistencies between free and occupied cells within the grid map M while incrementally building such map. If an occupied measurement is detected on a location previously set as free, then it belongs to a moving object.…”

Section: A Lidar Processingmentioning

confidence: 99%

“…We propose sparse version of HOG descriptor (S-HOG) that focuses on specific areas of an image patch. This allows us to reduce the common high-dimensional HOG descriptor [12]. Fig.…”

Section: B Camera Imagesmentioning

confidence: 99%

See 2 more Smart Citations

Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking

Chavéz-García

Aycard

2016

IEEE Trans. Intell. Transport. Syst.

Self Cite

296

131

View full text Add to dashboard Cite

International audience—The accurate detection and classification of moving objects is a critical aspect of Advanced Driver Assistance Systems (ADAS). We believe that by including the objects classification from multiple sensors detections as a key component of the object's representation and the perception process, we can improve the perceived model of the environment. First, we define a composite object representation to include class information in the core object's description. Second , we propose a complete perception fusion architecture based on the Evidential framework to solve the Detection and Tracking of Moving Objects (DATMO) problem by integrating the composite representation and uncertainty management. Finally, we integrate our fusion approach in a real-time application inside a vehicle demonstrator from the interactIVe IP European project which includes three main sensors: radar, lidar and camera. We test our fusion approach using real data from different driving scenarios and focusing on four objects of interest: pedestrian, bike, car and truck

show abstract

Section: A Lidar Processingmentioning

confidence: 99%

Section: A Lidar Processingmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking

Chavéz-García

Aycard

2016

IEEE Trans. Intell. Transport. Syst.

Self Cite

296

131

View full text Add to dashboard Cite

show abstract

“…Correct detection of moving objects is the necessary prerequisite to object tracking system. Research efforts have shown the feasibility of detecting moving objects around the car using various sensors, such as video camera [3, 4], light detection and ranging (LiDAR) [5, 6], and radar [7], or through multi‐sensor fusion [8–11]. Camera is easy to be applied and operated in low cost; however, it is hard to measure the distance of the identified objects and camera‐based object detection approaches have lower efficiency under complex shadow and bad weather.…”

Section: Introductionmentioning

confidence: 99%

Feature‐based detection and classification of moving objects using LiDAR sensor

Guo

Cai

Jiang

et al. 2019

IET Intelligent Transport Systems

View full text Add to dashboard Cite

“…active, tracked, inactive and lost), are used in the model with Markov decision processes to manage the lifetime of a track (Xiang et al , 2015), but an inactive target remains so forever without considering false missing cases. Besides, rather than just monitoring frontal objects (Chavez-Garcia et al , 2014), we consider the perception of objects in 360 degrees in this paper, which is more difficult to keep their tracks constantly.…”

Section: Introductionmentioning

confidence: 99%

A novel intelligent vehicle risk assessment method combined with multi-sensor fusion in dense traffic environment

Zheng

Huang

et al. 2018

JICV

View full text Add to dashboard Cite

Purpose-The purpose of this paper is to accurately capture the risks which are caused by each road user in time. Design/methodology/approach-The authors proposed a novel risk assessment approach based on the multi-sensor fusion algorithm in the real traffic environment. Firstly, they proposed a novel detection-level fusion approach for multi-object perception in dense traffic environment based on evidence theory. This approach integrated four states of track life into a generic fusion framework to improve the performance of multi-object perception. The information of object type, position and velocity was accurately obtained. Then, they conducted several experiments in real dense traffic environment on highways and urban roads, which enabled them to propose a novel road traffic risk modeling approach based on the dynamic analysis of vehicles in a variety of driving scenarios. By analyzing the generation process of traffic risks between vehicles and the road environment, the equivalent forces of vehicle-vehicle and vehicle-road were presented and theoretically calculated. The prediction steering angle and trajectory were considered in the determination of traffic risk influence area. Findings-The results of multi-object perception in the experiments showed that the proposed fusion approach achieved low false and missing tracking, and the road traffic risk was described as a field of equivalent force. The results extend the understanding of the traffic risk, which supported that the traffic risk from the front and back of the vehicle can be perceived in advance. Originality/value-This approach integrated four states of track life into a generic fusion framework to improve the performance of multi-object perception. The information of object type, position and velocity was used to reduce erroneous data association between tracks and detections. Then, the authors conducted several experiments in real dense traffic environment on highways and urban roads, which enabled them to propose a novel road traffic risk modeling approach based on the dynamic analysis of vehicles in a variety of driving scenarios. By analyzing the generation process of traffic risks between vehicles and the road environment, the equivalent forces of vehicle-vehicle and vehicle-road were presented and theoretically calculated.

show abstract

Fusion at detection level for frontal object perception

Cited by 13 publications

References 6 publications

Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking

Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking

Feature‐based detection and classification of moving objects using LiDAR sensor

A novel intelligent vehicle risk assessment method combined with multi-sensor fusion in dense traffic environment

Contact Info

Product

Resources

About