A Real-Time Method to Estimate Speed of Object Based on Object Detection and Optical Flow Calculation

Liu, Kaizhan; Ye, Yunming; Li, Xutao; Li, Yan

doi:10.1088/1742-6596/1004/1/012003

Cited by 5 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first difference between our proposed method and other methods, as shown in Table 6 , is that we also provide the location of each object in the semantically segmented scene, providing contextual detection for urban area. The other difference between [ 11 ] and our method is that, instead of the k-means algorithm for object–background separation, we use the Otsu method. This method is fast compared to the k-means, which is slow for more extensive datasets, and provides an optimal threshold since it operates on a histogram.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Contextual Detection of Pedestrians and Vehicles in Orthophotography by Fusion of Deep Learning Algorithms

Ansarnia

Tisserand

Schweitzer

et al. 2022

Sensors

View full text Add to dashboard Cite

In the context of smart cities, monitoring pedestrian and vehicle movements is essential to recognize abnormal events and prevent accidents. The proposed method in this work focuses on analyzing video streams captured from a vertically installed camera, and performing contextual road user detection. The final detection is based on the fusion of the outputs of three different convolutional neural networks. We are simultaneously interested in detecting road users, their motion, and their location respecting the static environment. We use YOLOv4 for object detection, FC-HarDNet for background semantic segmentation, and FlowNet 2.0 for motion detection. FC-HarDNet and YOLOv4 were retrained with our orthophotographs dataset. The last step involves a data fusion module. The presented results show that the method allows one to detect road users, identify the surfaces on which they move, quantify their apparent velocity, and estimate their actual velocity.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In [ 11 ], the authors use YOLOv2 for object detection and FlowNet for optical flow estimation. They also merge their results to estimate the speed of detected objects, without providing the direction of the velocity vector.…”

Section: Introductionmentioning

confidence: 99%

Contextual Detection of Pedestrians and Vehicles in Orthophotography by Fusion of Deep Learning Algorithms

Ansarnia

Tisserand

Schweitzer

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Previously, researchers have developed networks that jointly perform the functions of apparent motion analysis and object detection. Liu et al [15] introduce a method to real-time estimate the speed of an object by combining two CNNs: YOLOv2 and FlowNet. This was destined to be applied to robotics and autonomous driving.…”

Section: Related Workmentioning

confidence: 99%

Urban road users detection and velocity estimation from top-view fish-eye imagery under low light conditions

Ansarnia

Tisserand

Trémeau³

et al. 2022

IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society

View full text Add to dashboard Cite

In this study we present a technique which performs pedestrians and vehicles detection through the use of off-the-shelf object detectors alongside existing optical flow based velocity estimation techniques. Road users detection and apparent movement quantification are carried out respectively by YOLOv4 and FlowNet2.0. The speed of the users is then estimated from the average optical flow in each bounding box. Experimental results show that our proposed methods can effectively detect road users and estimate their velocity and movement direction under low light and low contrast urban video scenes. The videos are made with a low cost fish-eye RGB camera placed in a vertical position at a height of less than 10 m. The estimated speed by taking into account the deformations generated by the wide-angle lens, is in very good agreement with reality.

show abstract

“…Of all the vision-based methods, the optical flow algorithm has received more attention in computer vision research because it does not spray the speckle pattern or install high contrast markers on structure. [15][16][17] Optical flow refers to the estimation of a vector field of local displacement for a sequence of images. In general, the existing optical flow can be divided into dense optical flow 18 and sparse optical flow.…”

Section: Introductionmentioning

confidence: 99%

“…This is a major drawback as it is not always possible or desirable to visually mark RC structures, especially surface preparation for large‐scale RC structures. Of all the vision‐based methods, the optical flow algorithm has received more attention in computer vision research because it does not spray the speckle pattern or install high contrast markers on structure 15–17 …”

Section: Introductionmentioning

confidence: 99%

Marker‐free vision‐based method for vibration measurements of RC structure under seismic vibration

Cun

Wang

Zhou

et al. 2022

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

The seismic vibration measurement of reinforced concrete (RC) structures is an important aspect of post‐disaster reconstruction. Unfortunately, the existing method of installing sensors on walls and columns is prohibitively expensive, and the measurement signals are prone to loss during seismic vibration. In this paper, a marker‐free measurement method based on the Lucas‐Kanade (L‐K) optical flow algorithm for vibration measurements of RC structures under seismic vibration has been developed. In addition, to improve the accuracy of L‐K optical flow in dealing with the RC structure under seismic vibration, a new approach for selecting the feature point that is used to solve the restrictions of manual marking, as well as an adaptive matched window strategy that uses different sizes of matched window along the motion to replace the fixed matched window in the original L‐K algorithm, are proposed. The precision of the proposed method is first validated by comparing it to the original L‐K optical flow algorithm. Then, compare its precision and efficiency to the existing vision‐based methods, including feature matching (FM) and digital image correlation (DIC). Finally, the behaviors of RC structures during seismic vibration, such as inter‐story drift, frequency, and strain, are investigated. The results show that, when compared to the original L‐K optical flow algorithm and other vision‐based methods, the proposed method can accurately and efficiently measure motion without spraying speckle or high contrast markers on the structure's surface, and it enables the rapid diagnosis of structures affected by earthquakes.

show abstract

A Real-Time Method to Estimate Speed of Object Based on Object Detection and Optical Flow Calculation

Cited by 5 publications

References 1 publication

Contextual Detection of Pedestrians and Vehicles in Orthophotography by Fusion of Deep Learning Algorithms

Contextual Detection of Pedestrians and Vehicles in Orthophotography by Fusion of Deep Learning Algorithms

Urban road users detection and velocity estimation from top-view fish-eye imagery under low light conditions

Marker‐free vision‐based method for vibration measurements of RC structure under seismic vibration

Contact Info

Product

Resources

About