Video analysis for traffic anomaly detection using support vector machines

Batapati, Praveen; Tran, Duy; Sheng, Weihua; Liu, Meiqin; Zeng, Ruili

doi:10.1109/wcica.2014.7053655

Cited by 8 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Anomali durumunun tespiti için videonun analiz verilerinden çıkarımlar yapılarak ilgili anomali durum değerlendirmesi yapılır. Bu değerlendirme izlenen bir trafik akış videosunda yol şeridinde ters giden(hareket yönü), yol için belirlenen hız limitini(hızı aşan) aşan veya yolda konumu durağan olan araçların davranışları anomaliye örnek gösterilebilir [12][13][14][15][16][17][18]…”

Section: Trafik Videolarının Analizinin öNemi Ve Anomali Kavramıunclassified

Trafik Video Analiz Verilerinden Anomali Tespit ve Diferansiyel Gelişim Algoritması Uç Öğrenme Makinesi ile Sınıflandırma

Avcı

Sönmez

2021

International Journal of Innovative Engineering Applications

View full text Add to dashboard Cite

Kameralar ile elde edilen videolarda hareketli nesne tespit ve takibi ile nesne hakkında anlamlı ve yorumlanabilir bilgi elde edilmesi süreci, video analizi olarak tanımlanabilir. Karayolu trafik akış videolarının analizi ise hareket eden nesnelerin (taşıt ve yaya) izlenen yol için belirlenen kurallar dışında davranış sergilemeleri (anomali) durumunun tespit ve uyarı sistemi olarak ifade edilebilir. Bu çalışmada karayolu trafik akış videolarında hareket eden nesnelerin anomali davranışlarını tespit ederek verileri makine öğrenmesi yöntemleri ile sınıflandırma yapılmıştır. Çalışma üç aşamadan oluşmaktadır. Birinci aşamada hareketli nesnenin tespiti için arka/ön plan bölütleme yöntemlerinden Gauss Karışım Modeli (GKM) ve nesnenin videoda takibi yapılabilmesi için Kalman Filtre-Macar Algoritması yöntemleri kullanılmıştır. İkinci aşamada tespit edilen nesneye ait koordinat bilgilerini kullanarak konum, süre, hız ve şekil verileri elde edilmiştir. Hazırlanan özgün algoritmaya dayalı özellik çıkarma yazılımı ile nesneler için anomali durumlarını içeren özellikler tablosu oluşturulmuştur. Son aşamada ise özellik tablosundaki veriler; Uç Öğrenme Makine (UÖM) yönteminin, gizli katmandaki nöron sayıları ve aktivasyon fonksiyonları Diferansiyel Gelişim Algoritması (DGA) ile optimize edilerek geliştirilen DGAUÖM yöntemi ile sınıflandırma yapılmıştır. Geliştirilen yöntem ile elde edilen sonuçlar diğer makine öğrenme yöntem (Naive Bayes, Destek Vektör Makinesi ve Yapay Sinir Ağı) sonuçları ile karşılaştırılmış ve başarım %100 ile en yüksek çıkmıştır.

show abstract

Section: Trafik Videolarının Analizinin öNemi Ve Anomali Kavramıunclassified

Trafik Video Analiz Verilerinden Anomali Tespit ve Diferansiyel Gelişim Algoritması Uç Öğrenme Makinesi ile Sınıflandırma

Avcı

Sönmez

2021

International Journal of Innovative Engineering Applications

View full text Add to dashboard Cite

show abstract

“…According to this principle, separation and differentiation of the motion from the background is done by comparing pixel differences at the same coordinates of the examined image with the reference image, either with a predetermined threshold value or with a statistical approach to these differences [1,2,8,11,12].…”

Section: Video Analysismentioning

confidence: 99%

“…Analysis of highway traffic flow footage may be defined as classification of anomaly described as illegal behaviour by detection and tracking of moving objects in the video streams from recording device hardware, and prediction thereof [9][10][11][12]. Systems consisting of hardware and software enabling autonomous monitoring of the traffic flow provide us with assessable and interpretable information.…”

Section: Introductionmentioning

confidence: 99%

“…Collection of these data by computer-aided autonomous systems reduces the margin of human error and increases computer control and the accuracy of the data in the assessment. This, in turn, yields high-performance warning systems for use in highway traffic which is monitored for security [11][12][13][14][15]. The objective of this study is to detect abnormal behaviours of moving objects from highway traffic flow footage, and to classify them and make a prediction of future state thereof by using artificial learning methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach in Analyzing Traffic Flow by Extreme Learning Machine Method

2019

View full text Add to dashboard Cite

The objective of this study is to detect abnormal behaviours of moving objects captured in highway traffic flow footages, classify them by using artificial learning methods, and lastly to predict the future thereof (regression). To this end, the system being the object of the design and application consists of three stages. In the first stage, to detect the moving object in the video, background/foreground segmentation method of Mixture of Gaussian (MOG), and to track the moving object, Kalman Filter-Hungarian algorithm method have been used. In the second stage, by using the coordinates of the object, such details as location, distance in terms of time, and speed of the object are obtained, and by using total pixel count data relating to the shape of the object are obtained. The software based on the specifically elaborated algorithm compares these data with the data in the table of rules set down for the road under surveillance, and generates an attribute table comprising anomalies of the objects in the video. In the last stage, however, the data included in the attribute table have been classified and predictions by the artificial learning method, Extreme Learning Machine (ELM) made.

show abstract

“…In supervised anomaly detection technologies, support vector machines (SVM) 12 and artificial neural networks 13 perform well, especially for multiclassification detection problems. Semi‐supervised anomaly detection technologies are well‐known for nice outcomes only with normal labeled samples, mainly containing One‐class SVMs 14 and autoencoders 7 .…”

Section: Introductionmentioning

confidence: 99%

An improved agglomerative hierarchical clustering anomaly detection method for scientific data

Shi

Zhao

Zhong

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Anomaly detection tries to find out the data that disobeys the rule of majority data or expected patterns. The traditional hierarchical clustering algorithms have been adopted to detect anomaly, but have the disadvantages of low effectiveness and unstability. So we propose an improved agglomerative hierarchical clustering method for anomaly detection. It dynamically adjusts the optimum clustering number according to the self-defined criterion to save the trouble of manually picking clustering number, and determines the optimum clustering distance mode according to cophenetic correlation coefficient to reduce the procedure of manually testing the suitable distance mode in each iteration. The performances of proposed method are verified on tensile test, HTRU2 and credit card dataset. Compared with the traditional methods, our method possesses the most comprehensive performance (the highest F-measure with less iterations), which shows effectiveness of anomaly detection. And compared with the traditional methods (single, complete, average, and centroid mode), our method achieves the best performance on tensile test and HTRU2 dataset, showing stronger generalization. Compared with other methods (Decision + Gradient Boosted Tree, Decision Trees + Decision Stump, etc) on credit card dataset, our method obtains similar accuracy, and ranks in the top level in the aspect of sensitivity.

show abstract

Video analysis for traffic anomaly detection using support vector machines

Cited by 8 publications

References 5 publications

Trafik Video Analiz Verilerinden Anomali Tespit ve Diferansiyel Gelişim Algoritması Uç Öğrenme Makinesi ile Sınıflandırma

Trafik Video Analiz Verilerinden Anomali Tespit ve Diferansiyel Gelişim Algoritması Uç Öğrenme Makinesi ile Sınıflandırma

A Novel Approach in Analyzing Traffic Flow by Extreme Learning Machine Method

An improved agglomerative hierarchical clustering anomaly detection method for scientific data

Contact Info

Product

Resources

About