Vehicle detection, counting and classification in various conditions

Kamkar, Shiva; Safabakhsh, Reza

doi:10.1049/iet-its.2015.0157

Cited by 79 publications

(34 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, there are many selected and extracted features [7,9,10,32,44,45,46] such as: wave length, mean, variance, peak, valley, acreage, acoustic signals, Histogram Oriented Gradients (HOG) features, the vehicle length, Grey-Level Co-occurrence matrix features, low level features, area, width, height, centroid, and bounding box. In the classification stage, these features are employed to classify the vehicles into several classes; the most used are small, medium, and large.…”

Section: Related Workmentioning

confidence: 99%

Vehicle Detection with Occlusion Handling, Tracking, and OC-SVM Classification: A High Performance Vision-Based System

Velazquez-Pupo

Sierra-Romero

Torres-Roman

et al. 2018

Sensors

View full text Add to dashboard Cite

This paper presents a high performance vision-based system with a single static camera for traffic surveillance, for moving vehicle detection with occlusion handling, tracking, counting, and One Class Support Vector Machine (OC-SVM) classification. In this approach, moving objects are first segmented from the background using the adaptive Gaussian Mixture Model (GMM). After that, several geometric features are extracted, such as vehicle area, height, width, centroid, and bounding box. As occlusion is present, an algorithm was implemented to reduce it. The tracking is performed with adaptive Kalman filter. Finally, the selected geometric features: estimated area, height, and width are used by different classifiers in order to sort vehicles into three classes: small, midsize, and large. Extensive experimental results in eight real traffic videos with more than 4000 ground truth vehicles have shown that the improved system can run in real time under an occlusion index of 0.312 and classify vehicles with a global detection rate or recall, precision, and F-measure of up to 98.190%, and an F-measure of up to 99.051% for midsize vehicles.

show abstract

Section: Related Workmentioning

confidence: 99%

Vehicle Detection with Occlusion Handling, Tracking, and OC-SVM Classification: A High Performance Vision-Based System

Velazquez-Pupo

Sierra-Romero

Torres-Roman

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Normally, robust object detection and tracking are necessary for event localization. In order to identify object movements, we compare the performance of vehicle localization of the active basis model of [11], the Viola-Jones cascade detector of [23], the deformable part model of [4], and our proposed method. The active basis model and the V-J cascade detector perform well for rearview vehicles, but it is difficult to train them for accurate vehicle event localization in cases of other viewing-angles (see the JINAN data-set results).…”

Section: Methodsmentioning

confidence: 99%

“…A diversity of feature-vector representation schemes has been proposed for object detection in complex scenes. The active basis model [24] has been widely employed for vehicle detection [11,16] in traffic surveillance. With the assistance of a shared skeleton method, it can be easily trained with a considerable detection performance.…”

Section: Related Workmentioning

confidence: 99%

Local Fast R-CNN Flow for Object-Centric Event Recognition in Complex Traffic Scenes

Yang

Yan

et al. 2018

Image and Video Technology

View full text Add to dashboard Cite

This paper presents a solution for an integrated object-centric event recognition problem for intelligent traffic supervision. We propose a novel event-recognition framework using deep local flow in a fast regionbased convolutional neural network (R-CNN). First, we use a fine-tuned fast R-CNN to accurately extract multi-scale targets in the open environment. Each detected object corresponds to an event candidate. Second, a deep belief propagation method is proposed for the calculation of local fast R-CNN flow (LFRCF) between local convolutional feature matrices of two non-adjacent frames in a sequence. Third, by using the LFRCF features, we can easily identify the moving pattern of each extracted object and formulate a conclusive description of each event candidate. The contribution of this paper is to propose an optimized framework for accurate event recognition. We verify the accuracy of multi-scale object detection and behavior recognition in extensive experiments on real complex road-intersection surveillance videos.

show abstract

“…There are many typical features that can be applied to the VTR, such as edge based feature [2,3], color based feature [4], symmetry based feature [5][6][7], SIFT descriptor based feature [8,9], HOG descriptor based feature [10], and Gabor filter based feature [11]. The edge based feature extraction methods extract the edge of vehicle image by a certain edge operator, such as Sobel operator.…”

Section: Introductionmentioning

confidence: 99%

Vehicle Type Recognition Combining Global and Local Features via Two-Stage Classification

Sun

Zhang

Shi

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This study proposes a new vehicle type recognition method that combines global and local features via a two-stage classification. To extract the continuous and complete global feature, an improved Canny edge detection algorithm with smooth filtering and non-maxima suppression abilities is proposed. To extract the local feature from four partitioned key patches, a set of Gabor wavelet kernels with five scales and eight orientations is introduced. Different from the single-stage classification, where all features are incorporated into one classifier simultaneously, the proposed two-stage classification strategy leverages two types of features and classifiers. In the first stage, the preliminary recognition of large vehicle or small vehicle is conducted based on the global feature via a -nearest neighbor probability classifier. Based on the preliminary result, the specific recognition of bus, truck, van, or sedan is achieved based on the local feature via a discriminative sparse representation based classifier. We experiment with the proposed method on the public and established datasets involving various challenging cases, such as partial occlusion, poor illumination, and scale variation. Experimental results show that the proposed method outperforms existing state-of-the-art methods.

show abstract

Vehicle detection, counting and classification in various conditions

Cited by 79 publications

References 26 publications

Vehicle Detection with Occlusion Handling, Tracking, and OC-SVM Classification: A High Performance Vision-Based System

Vehicle Detection with Occlusion Handling, Tracking, and OC-SVM Classification: A High Performance Vision-Based System

Local Fast R-CNN Flow for Object-Centric Event Recognition in Complex Traffic Scenes

Vehicle Type Recognition Combining Global and Local Features via Two-Stage Classification

Contact Info

Product

Resources

About