scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Video Based Vehicle Counting Using Deep Learning Algorithms

01 Jan 2020-Vol. 2020, pp 142-147
TL;DR: This paper provides a survey on various techniques available for vehicle detection and tracking, and shows remarkable improvements compared to conventional image processing techniques by removing the weakness in the conventional techniques.
Abstract: Traffic density in roads has been increasing day by day which needs intelligent transportation system that can handle the traffic. Traffic management has become inevitable for smart cities. The enormous increase in vehicle numbers has generated more pressure to manage traffic congestion especially during peak hours. If the traffic congestion at a particular point of time can be found, then that information can be useful for managing the traffic in different lanes and change the traffic light cycle dynamically according to the vehicle count in different lanes. In recent years video surveillance and monitoring has been gaining importance. Video can be analyzed which can be used to find the traffic density. Many useful information can be obtained by video processing like real time traffic density. Vehicle counting can be done by detecting the object, tracking it and then finally counting the objects. Many different techniques are available for object detection and tracking. Deep learning techniques for object detection led to remarkable improvements compared to conventional image processing techniques by removing the weakness in the conventional techniques. This paper provides a survey on various techniques available for vehicle detection and tracking.
Citations
More filters
Journal ArticleDOI
01 Dec 2020
TL;DR: This paper studies the multi-class multi-movement vehicle counting problem, overview the state-of-the-art methods designed to solve this problem, and presents a series of comprehensive experiments, using traffic footage with O(5) vehicles captured from 20 different vantage points and covering various lighting and weather conditions.
Abstract: With the advent of accurate deep learning-based object detection methods, it is now possible to employ prevalent city-wide traffic and intersection cameras to derive actionable insights for improving traffic, road infrastructure, and transit. A crucial tool in signal timing planning is capturing accurate movement- and class-specific vehicle counts. To be useful in online intelligent transportation systems, methods designed for this task must not only be accurate in their counting, but should also be efficient. In this paper, we study the multi-class multi-movement vehicle counting problem, overview the state-of-the-art methods designed to solve this problem, and present a series of comprehensive experiments, using traffic footage with O(5) vehicles captured from 20 different vantage points and covering various lighting and weather conditions. Our survey aims to answer the question whether we are ready to leverage traffic cameras for real-time automatic vehicle counting. The results of our analysis show several promising approaches and identify areas where additional improvement is needed.

4 citations


Cites background from "Video Based Vehicle Counting Using ..."

  • ...Mirthubashini and Santhi [45] surveyed various vehicle detection and tracking techniques, including both deep-learning and classical detection and tracking methods, such as Gaussian mixture models (GMM) [60] and Mixture of Gaussians (MoG) + Support Vector Machines (SVM) [2]....

    [...]

Journal ArticleDOI
TL;DR: In this paper, the authors proposed an efficient approach that uses deep learning concepts and correlation filters for multi-object counting and tracking and evaluated the performance of the proposed system using a dataset consisting of 16 videos with different features.
Abstract: Object counting is an active research area that gained more attention in the past few years. In smart cities, vehicle counting plays a crucial role in urban planning and management of the Intelligent Transportation Systems (ITS). Several approaches have been proposed in the literature to address this problem. However, the resulting detection accuracy is still not adequate. This paper proposes an efficient approach that uses deep learning concepts and correlation filters for multi-object counting and tracking. The performance of the proposed system is evaluated using a dataset consisting of 16 videos with different features to examine the impact of object density, image quality, angle of view, and speed of motion towards system accuracy. Performance evaluation exhibits promising results in normal traffic scenarios and adverse weather conditions. Moreover, the proposed approach outperforms the performance of two recent approaches from the literature

2 citations

Journal ArticleDOI
TL;DR: In this article , a spotted hyena optimizer with deep learning-enabled vehicle counting and classification (SHODL-VCC) model was proposed for the ITSs to achieve accurate vehicle detection and counting from traffic videos.
Abstract: <abstract> <p>Traffic surveillance systems are utilized to collect and monitor the traffic condition data of the road networks. This data plays a crucial role in a variety of applications of the Intelligent Transportation Systems (ITSs). In traffic surveillance, it is challenging to achieve accurate vehicle detection and count the vehicles from traffic videos. The most notable difficulties include real-time system operations for precise classification, identification of the vehicles' location in traffic flows and functioning around total occlusions that hamper the vehicle tracking process. Conventional video-related vehicle detection techniques such as optical flow, background subtraction and frame difference have certain limitations in terms of efficiency or accuracy. Therefore, the current study proposes to design the spotted hyena optimizer with deep learning-enabled vehicle counting and classification (SHODL-VCC) model for the ITSs. The aim of the proposed SHODL-VCC technique lies in accurate counting and classification of the vehicles in traffic surveillance. To achieve this, the proposed SHODL-VCC technique follows a two-stage process that includes vehicle detection and vehicle classification. Primarily, the presented SHODL-VCC technique employs the RetinaNet object detector to identify the vehicles. Next, the detected vehicles are classified into different class labels using the deep wavelet auto-encoder model. To enhance the vehicle detection performance, the spotted hyena optimizer algorithm is exploited as a hyperparameter optimizer, which considerably enhances the vehicle detection rate. The proposed SHODL-VCC technique was experimentally validated using different databases. The comparative outcomes demonstrate the promising vehicle classification performance of the SHODL-VCC technique in comparison with recent deep learning approaches.</p> </abstract>
References
More filters
Journal ArticleDOI
TL;DR: This paper presents vehicle classification and traffic density calculation methods using neural networks and reports results from real traffic videos obtained from Istanbul Traffic Management Company (ISBAK).
Abstract: It is important to know the road traffic density real time especially in mega cities for signal control and effective traffic management. In recent years, video monitoring and surveillance systems have been widely used in traffic management. Hence, traffic density estimation and vehicle classification can be achieved using video monitoring systems. In most vehicle detection methods in the literature, only the detection of vehicles in frames of the given video is emphesized. However, further analysis is needed in order to obtain the useful information for traffic management such as real time traffic density and number of vehicle types passing these roads. This paper presents vehicle classification and traffic density calculation methods using neural networks. The paper also reports results from real traffic videos obtained from Istanbul Traffic Management Company (ISBAK).

126 citations


"Video Based Vehicle Counting Using ..." refers methods in this paper

  • ...Background Subtraction[8] 94% Background Subtraction,Interframe difference[9] 90....

    [...]

  • ...A Moving Object Detector (MOD), Vehicle Identifier (VI), Traffic Density Calculator (TDC) are used in [8]....

    [...]

Journal ArticleDOI
TL;DR: It is shown in experiments that Faster RCNN outperforms MoG in detection of vehicles that are static, overlapping or in night time conditions, and faster RCNN also outperforms SVM for the task of classifying vehicle types based on appearances.

75 citations


"Video Based Vehicle Counting Using ..." refers methods in this paper

  • ...Faster RCNN, Kernalized Correlation Filters[7] 69%...

    [...]

  • ...Two different techniques for detecting objects in a video were discussed in [7]....

    [...]

Journal ArticleDOI
TL;DR: The proposed video-based vehicle counting framework is capable of acquiring reliable traffic flow information, which is likely applicable to intelligent traffic control and dynamic signal timing.
Abstract: The continuous development in the construction of transportation infrastructure has brought enormous pressure to traffic control. Accurate and detailed traffic flow information is valuable for an effective traffic control strategy. This paper proposes a video-based vehicle counting framework using a three-component process of object detection, object tracking, and trajectory processing to obtain the traffic flow information. First, a dataset for vehicle object detection (VDD) and a standard dataset for verifying the vehicle counting results (VCD) were established. The object detection was then completed by deep learning with VDD. Using this detection, a matching algorithm was designed to perform multi-object tracking in combination with a traditional tracking method. Trajectories of the moving objects were obtained using this approach. Finally, a trajectory counting algorithm based on encoding is proposed. The vehicles were counted according to the vehicle categories and their moving route to obtain detailed traffic flow information. The results demonstrated that the overall accuracy of our method for vehicle counting can reach more than 90%. The running rate of the proposed framework is 20.7 frames/s on the VCD. Therefore, the proposed vehicle counting framework is capable of acquiring reliable traffic flow information, which is likely applicable to intelligent traffic control and dynamic signal timing.

72 citations


"Video Based Vehicle Counting Using ..." refers background in this paper

  • ...Three different kinds of roads namely, cross roads, T junction and straight roads were considered in [4] for better accuracy....

    [...]

  • ...Algorithm Used Accuracy YoloV3,Keranalized Correlation filters[4] 86....

    [...]

Journal ArticleDOI
TL;DR: The present methodology does not regard an individual vehicle as an object to be detected separately; rather, it collectively counts the number of vehicles as a human would and outperforms existing schemes.
Abstract: Existing methodologies to count vehicles from a road image have depended upon both hand-crafted feature engineering and rule-based algorithms. These require many predefined thresholds to detect and track vehicles. This paper provides a supervised learning methodology that requires no such feature engineering. A deep convolutional neural network was devised to count the number of vehicles on a road segment based solely on video images. The present methodology does not regard an individual vehicle as an object to be detected separately; rather, it collectively counts the number of vehicles as a human would. The test results show that the proposed methodology outperforms existing schemes.

71 citations


Additional excerpts

  • ...A deep convolutional neural network based on video images in [10] to count the number of vehicles on a road segment Vehicles are counted manually in order to add a label to the image within each input image....

    [...]

Journal ArticleDOI
TL;DR: In this method, a deep network is designed for hierarchical semantic feature extraction and different from traditional deep regression networks, which usually directly utilize mean squared error as loss function, a robust metric learning is employed to effectively train the network.
Abstract: Congestion detection is an important aspect of vehicular management. However, most of the existing algorithms are insufficient for real applications. Traditional features are not discriminative which results in rather poor performance under complex scenarios. The deep features can better represent high-level information, but the training of deep network for regression is difficult. To promote the congestion detection, a robust hierarchical deep learning is proposed for the task. In this method, a deep network is designed for hierarchical semantic feature extraction. Different from traditional deep regression networks, which usually directly utilize mean squared error as loss function, a robust metric learning is employed to effectively train the network. Based on this, multiple networks are combined together to further improve the generalization ability. Extensive experiments are conducted and the proposed model is confirmed to be effective.

46 citations


"Video Based Vehicle Counting Using ..." refers background in this paper

  • ...A hierarchical deep learning approach for congestion detection is discussed in [11]....

    [...]