Robust Vehicle Detection and Counting Algorithm Employing a Convolution Neural Network and Optical Flow

Gomaa, Ahmed; Abdelwahab, Moataz M.; Abo‐Zahhad, Mohammed; Minematsu, Toshio; Taniguchi, Rin Ichiro

doi:10.3390/s19204588

Cited by 53 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, we define the state based on the position of vehicles at an intersection. Through vehicle detection technology [22], or other tools such as induction-loop and vehicular network, information of vehicle positions can be easily collected. In addition, vehicle positions reflect the traffic environment adequately and offer some detailed information, such as the queue length.…”

Section: State Representationmentioning

confidence: 99%

Double Deep Q-Network with a Dual-Agent for Traffic Signal Control

Fang

Sheng

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Adaptive traffic signal control (ATSC) based on deep reinforcement learning (DRL) has shown promising prospects to reduce traffic congestion. Most existing methods keeping traffic signal phases fixed adopt two agent actions to match a four-phase suffering unstable performance and undesirable operation in a four-phase signalized intersection. In this paper, a Double Deep Q-Network (DDQN) with a dual-agent algorithm is proposed to obtain a stable traffic signal control policy. Specifically, two agents are denoted by two different states and shift the control of green lights to make the phase sequence fixed and control process stable. State representations and reward functions are presented by improving the observability and reducing the leaning difficulty of two agents. To enhance the feasibility and reliability of two agents in the traffic control of the four-phase signalized intersection, a network structure incorporating DDQN is proposed to map states to rewards. Experiments under Simulation of Urban Mobility (SUMO) are carried out, and results show that the proposed traffic signal control algorithm is effective in improving traffic capacity.

show abstract

Section: State Representationmentioning

confidence: 99%

Double Deep Q-Network with a Dual-Agent for Traffic Signal Control

Fang

Sheng

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Mostly the CNN is applied in images which can be regarded as two-dimensional discrete signals. By applying CNN-based object detection methods, the vehicles were segmented from the background with class labels [ 27 , 28 , 29 ]. When calibrated with real world coordination systems, the spacing information of vehicles was accessed [ 18 ].…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Based Vehicle Detection and Classification Methodology Using Strain Sensors under Bridge Deck

Zhang

Dong

et al. 2020

Sensors

View full text Add to dashboard Cite

Vehicle detection and classification have become important tasks for traffic monitoring, transportation management and pavement evaluation. Nowadays there are sensors to detect and classify the vehicles on road. However, on one hand, most sensors rely on direct contact measurement to detect the vehicles, which have to interrupt the traffic. On the other hand, complex road scenes produce much noise to consider when to process the signals. In this paper, a data-driven methodology for the detection and classification of vehicles using strain data is proposed. The sensors are well arranged under the bridge deck without traffic interruption. Next, a cascade pre-processing method is applied for vehicle detection to eliminate in-situ noise. Then, a neural network model is trained to identify the close-range following vehicles and separate them by Non-Maximum Suppression. Finally, a deep convolutional neural network is designed and trained to identify the vehicle types based on the axle group. The methodology was applied in a long-span bridge. Three strain sensors were installed beneath the bridge deck for a week. High robustness and accuracy were obtained by these algorithms. The methodology proposed in this paper is an adaptive and promising method for vehicle detection and classification under complex noise. It would serve as a supplement to current transportation systems and provide reliable data for management and decision-making.

show abstract

“…Several recent studies, including [4], [5], [17], [18], have employed DNNs for traffic monitoring. Luo et al [4] used texture features to classify traffic congestion in videos without considering motion information.…”

Section: Related Workmentioning

confidence: 99%

Reliable and Rapid Traffic Congestion Detection Approach Based on Deep Residual Learning and Motion Trajectories

2020

View full text Add to dashboard Cite

Traffic congestion detection systems help manage traffic in crowded cities by analyzing videos of vehicles. Existing systems largely depend on texture and motion features. Such systems face several challenges, including illumination changes caused by variations in weather conditions, complexity of scenes, vehicle occlusion, and the ambiguity of stopped vehicles. To overcome these issues, this paper proposes a rapid and reliable traffic congestion detection method based on the modeling of video dynamics using deep residual learning and motion trajectories. The proposed method efficiently uses both motion and deep texture features to overcome the limitations of existing methods. Unlike other methods that simply extract texture features from a single frame, we use an efficient representation learning method to capture the latent structures in traffic videos by modeling the evolution of texture features. This representation yields a noticeable improvement in detection results under various weather conditions. Regarding motion features, we propose an algorithm to distinguish stopped vehicles and background objects, whereas most existing motion-based approaches fail to address this issue. Both types of obtained features are used to construct an ensemble classification model based on the support vector machine algorithm. Two benchmark datasets are considered to demonstrate the robustness of the proposed method: the UCSD dataset and NU1 video dataset. The proposed method achieves competitive results (97.64% accuracy) when compared to state-ofthe-art methods.

show abstract

Robust Vehicle Detection and Counting Algorithm Employing a Convolution Neural Network and Optical Flow

Cited by 53 publications

References 23 publications

Double Deep Q-Network with a Dual-Agent for Traffic Signal Control

Double Deep Q-Network with a Dual-Agent for Traffic Signal Control

Deep Learning Based Vehicle Detection and Classification Methodology Using Strain Sensors under Bridge Deck

Reliable and Rapid Traffic Congestion Detection Approach Based on Deep Residual Learning and Motion Trajectories

Contact Info

Product

Resources

About