Moving Object Detection Based on Background Compensation and Deep Learning

Zhu, Juncai; Wang, Zhizhong; Wang, Songwei; Chen, Shuli

doi:10.3390/sym12121965

Cited by 27 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Deep Learning (DL) has been proposed to achieve good results in detecting moving objects in the camera environment [8]. For example, Convolution Neural Networks (CNN) models in video processing have provided impressive results in tracking moving objects [9], Recurrent Neural Networks (RNN) models can be applied to various vision Data 2022, 7, 40 2 of 7 tasks that involve sequential inputs and outputs, such as detecting the activity of an object in time [10], or using You Only Look Once YOLO, a DL-based real-time object detection algorithm [11]. The tremendous success of road traffic monitoring systems has been made possible primarily by improvements in the methodology for moving objects, the availability of appropriate datasets, and the computational gains achieved with GPU cards.…”

Section: Discussionmentioning

confidence: 99%

Dataset of Annotated Virtual Detection Line for Road Traffic Monitoring

Namatēvs

Kadiķis

Zencovs

et al. 2022

Data

View full text Add to dashboard Cite

Monitoring, detection, and control of traffic is a serious problem in many cities and on roads around the world and poses a problem for effective and safe control and management of pedestrians with edge devices. Systems using the computer vision approach must ensure the safety of citizens and minimize the risk of traffic collisions. This approach is well suited for multiple object detection by automatic video surveillance cameras on roads, highways, and pedestrian walkways. A new Annotated Virtual Detection Line (AVDL) dataset is presented for multiple object detection, consisting of 74,108 data files and 74,108 manually annotated files divided into six classes: Vehicles, Trucks, Pedestrians, Bicycles, Motorcycles, and Scooters from the video. The data were captured from real road scenes using 50 video cameras from the leading video camera manufacturers at different road locations and under different meteorological conditions. The AVDL dataset consists of two directories, the Data directory and the Labels directory. Both directories provide the data as NumPy arrays. The dataset can be used to train and test deep neural network models for traffic and pedestrian detection, recognition, and counting.

show abstract

Section: Discussionmentioning

confidence: 99%

Dataset of Annotated Virtual Detection Line for Road Traffic Monitoring

Namatēvs

Kadiķis

Zencovs

et al. 2022

Data

View full text Add to dashboard Cite

show abstract

“…To achieve the initial separation of the object and background and output the bounding box of cows for pose estimation, we built a multiobject model prior to pose estimation. In recent years, much research has been conducted on multiobject detection [ 29 – 31 ]. In this study, the YOLO v4 network which is a one-stage object detection algorithm was used to carry out fast and accurate detection of multiple cows.…”

Section: Methodsmentioning

confidence: 99%

Multicow pose estimation based on keypoint extraction

et al. 2022

View full text Add to dashboard Cite

Automatic estimation of the poses of dairy cows over a long period can provide relevant information regarding their status and well-being in precision farming. Due to appearance similarity, cow pose estimation is challenging. To monitor the health of dairy cows in actual farm environments, a multicow pose estimation algorithm was proposed in this study. First, a monitoring system was established at a dairy cow breeding site, and 175 surveillance videos of 10 different cows were used as raw data to construct object detection and pose estimation data sets. To achieve the detection of multiple cows, the You Only Look Once (YOLO)v4 model based on CSPDarkNet53 was built and fine-tuned to output the bounding box for further pose estimation. On the test set of 400 images including single and multiple cows throughout the whole day, the average precision (AP) reached 94.58%. Second, the keypoint heatmaps and part affinity field (PAF) were extracted to match the keypoints of the same cow based on the real-time multiperson 2D pose detection model. To verify the performance of the algorithm, 200 single-object images and 200 dual-object images with occlusions were tested under different light conditions. The test results showed that the AP of leg keypoints was the highest, reaching 91.6%, regardless of day or night and single cows or double cows. This was followed by the AP values of the back, neck and head, sequentially. The AP of single cow pose estimation was 85% during the day and 78.1% at night, compared to double cows with occlusion, for which the values were 74.3% and 71.6%, respectively. The keypoint detection rate decreased when the occlusion was severe. However, in actual cow breeding sites, cows are seldom strongly occluded. Finally, a pose classification network was built to estimate the three typical poses (standing, walking and lying) of cows based on the extracted cow skeleton in the bounding box, achieving precision of 91.67%, 92.97% and 99.23%, respectively. The results showed that the algorithm proposed in this study exhibited a relatively high detection rate. Therefore, the proposed method can provide a theoretical reference for animal pose estimation in large-scale precision livestock farming.

show abstract

“…The authors reported a 94.1% improvement in vehicle detection accuracy. There is another study conducted by Zhu et al [22] on moving vehicles (airplane, car, and person) detection using the YOLOv3 in conjunction with background subtraction image frames in videos. They reported 91% mAP and 27 frames per second (FPS).…”

Section: Literature Reviewmentioning

confidence: 99%

Convolutional Neural Network for Overcrowded Public Transportation Pickup Truck Detection

Suttanuruk¹,

Jomnonkwao²,

Ratanavaraha³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Thailand has been on the World Health Organization (WHO)'s notorious deadliest road list for several years, currently ranking eighth on the list. Among all types of road fatalities, pickup trucks converted into vehicles for public transportation are found to be the most problematic due to their high occupancy and minimal passenger safety measures, such as safety belts. Passenger overloading is illegal, but it is often overlooked. The country often uses police checkpoints to enforce traffic laws. However, there are few or no highway patrols to apprehend offending drivers. Therefore, in this study, we propose the use of existing closed-circuit television (CCTV) traffic cameras with deep learning techniques to classify overloaded public transport pickup trucks (PTPT) to help reduce accidents. As the said type of vehicle and its passenger occupancy characteristics are unique, a new model is deemed necessary. The contributions of this study are as follows: First, we used various state-of-the-art object detection YOLOv5 (You Only Look Once) models to obtain the optimum overcrowded model pretrained on our manually labeled dataset. Second, we made our custom dataset available. Upon investigation, we compared all the latest YOLOv5 models and discovered that the YOLOv5L yielded the optimal performance with a mean average precision (mAP) of 95.1% and an inference time of 33 frames per second (FPS) on a graphic processing unit (GPU). We aim to deploy the selected model on traffic control computers to alert the police of such passenger-overloading violations. The use of a chosen algorithm is feasible and is expected to help reduce trafficrelated fatalities.

show abstract

Moving Object Detection Based on Background Compensation and Deep Learning

Cited by 27 publications

References 28 publications

Dataset of Annotated Virtual Detection Line for Road Traffic Monitoring

Dataset of Annotated Virtual Detection Line for Road Traffic Monitoring

Multicow pose estimation based on keypoint extraction

Convolutional Neural Network for Overcrowded Public Transportation Pickup Truck Detection

Contact Info

Product

Resources

About