Real Time Pedestrian and Object Detection and Tracking-based Deep Learning. Application to Drone Visual Tracking

Khemmar, Redouane; Gouveia, Matthias; Decoux, Benoît; Ertaud, Jean-Yves

doi:10.24132/csrn.2019.2902.2.5

Cited by 9 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We propose here to exploit the maturity of such methods in order to enhance the perception and the analysis of a niche area of application and road scene understanding. In this context, several works related to object detection, recognition and tracking have already been carried out in collaboration with SEGULA technologies, such as the tracking of a person by a drone [3], the detection and tracking of objects for the road smart mobility [4]. The goal is to propose new approaches of embedded vision dedicated to the detection of objects, their localisation as well as their tracking, which allow better performance in realistic and complex conditions.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Real-Time 3D Multi-Object Detection, Localisation, and Tracking: Application to Smart Mobility

Mauri

Khemmar

Decoux

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

In core computer vision tasks, we have witnessed significant advances in object detection, localisation and tracking. However, there are currently no methods to detect, localize and track objects in road environments, and taking into account real-time constraints. In this paper, our objective is to develop a deep learning multi object detection and tracking technique applied to road smart mobility. Firstly, we propose an effective detector-based on YOLOv3 which we adapt to our context. Subsequently, to localize successfully the detected objects, we put forward an adaptive method aiming to extract 3D information, i.e., depth maps. To do so, a comparative study is carried out taking into account two approaches: Monodepth2 for monocular vision and MADNEt for stereoscopic vision. These approaches are then evaluated over datasets containing depth information in order to discern the best solution that performs better in real-time conditions. Object tracking is necessary in order to mitigate the risks of collisions. Unlike traditional tracking approaches which require target initialization beforehand, our approach consists of using information from object detection and distance estimation to initialize targets and to track them later. Expressly, we propose here to improve SORT approach for 3D object tracking. We introduce an extended Kalman filter to better estimate the position of objects. Extensive experiments carried out on KITTI dataset prove that our proposal outperforms state-of-the-art approches.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning for Real-Time 3D Multi-Object Detection, Localisation, and Tracking: Application to Smart Mobility

Mauri

Khemmar

Decoux

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…But those methods still lack in precise evaluation. In this context, several works related to environment perception have already been carried out, such as the tracking of a person [5], the detection and tracking of objects for the road smart mobility [6] [7].…”

Section: Introductionmentioning

confidence: 99%

A new Evaluation Approach for Deep Learning-based Monocular Depth Estimation Methods

Mauri

Khemmar

Boutteau

et al. 2020

2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)

Self Cite

View full text Add to dashboard Cite

In smart mobility based road navigation, object detection, depth estimation and tracking are very important tasks for improvement of the environment perception quality. In the recent years, a surge of deep-learning based depth estimation methods for monocular cameras has lead to significant progress in this field. In this paper, we propose an evaluation of state-of-the-art depth estimation algorithms based on single single input on both the KITTI dataset and the recently published NUScenes dataset. The models evaluated in this paper include an unsupervised method (Monodepth2) and a supervised method (BTS). Our work lies in the elaboration of novel depth evaluation protocols, object depth evaluation and distance ranges evaluation. We validated our new protocols on both KITTI and NUScenes datasets, allowing us to get a more comprehensive evaluation for depth estimation, especially for applications in scene understanding for both road and rail environment.

show abstract

“…Two methods of object recognition were used in [Khe00]. This work focuses on new approaches in the embedded vision for object detection and tracking in drone visual control.…”

Section: Related Work On Pedestrian Detection and Recognitionmentioning

confidence: 99%

Detection of Dangerous Situations Near Pedestrian Crossings using In-Car Camera

Kubanek¹,

Karbowiak²,

Bobulski³

2023

Computer Science Research Notes

View full text Add to dashboard Cite

The paper presents a method for detecting dangerous situations near pedestrian crossings using an in-car camera system. The approach utilizes deep learning-based object detection to identify pedestrians and vehicles, analyzing their behavior to identify potential hazards. The system incorporates vehicle sensor data for enhanced accuracy. Evaluation results show high accuracy in detecting dangerous situations. The proposed system can potentially enhance pedestrian and driver safety in urban transportation.

show abstract

Real Time Pedestrian and Object Detection and Tracking-based Deep Learning. Application to Drone Visual Tracking

Cited by 9 publications

References 21 publications

Deep Learning for Real-Time 3D Multi-Object Detection, Localisation, and Tracking: Application to Smart Mobility

Deep Learning for Real-Time 3D Multi-Object Detection, Localisation, and Tracking: Application to Smart Mobility

A new Evaluation Approach for Deep Learning-based Monocular Depth Estimation Methods

Detection of Dangerous Situations Near Pedestrian Crossings using In-Car Camera

Contact Info

Product

Resources

About