用於真實世界交通監控系統的高精確度移動物體偵測方法

近年來，具有自動監測功能來偵測移動物體的無線視訊監控已成為智慧型運輸系統管理的主要技術。智慧型運輸系統可藉由精確地區別車輛以及背景物體來取得道路上目前的車流，或是偵測以及追蹤特定的車輛來達到紓解交通阻塞、提升運輸安全以及最佳化交通流量。然而，無線視訊監控在現實網路頻寬的限制下，視訊通訊往往會受到網路壅塞以及頻寬不穩定的影響，造成視訊影像品質降低，特別是在無線視訊通訊系統下所傳輸的視訊資料會產生許多問題。同時，無線視訊監控運作於現實的氣候環境中，視訊品質也會遭受能見度不足所影響。上述這兩個問題將會造成傳統的移動物體偵測技術上的困難，而無法得到有效的偵測結果。因此，本文提出一種基於費雪線性判別的雙暗通道統計和小腦模型網路的新式移動物體偵測方法，於上述之現實環境中，來達到完整且精確的移動物體偵測。偵測結果顯示本文所提出的方法確實有能力可以在現實惡劣的氣候環境中且使用變動位元率的視訊串流下來達到高精確度的移動物體偵測。

關鍵字

智慧型運輸系統；無線視訊監控；視訊品質

並列摘要

Automated motion detection, which segments moving objects from video streams, is the key technology of traffic surveillance systems for traffic management. Traffic surveillance systems use video communication over real-world networks with limited bandwidth, which frequently suffers because of either network congestion or unstable bandwidth. Evidence supporting these problems abounds in publications about wireless video communication. Moreover, the visibility of videos will generally become degraded when captured during inclement weather conditions, such as haze and sandstorm. Video degradation can cause problems for automated motion detection, which must operate under a wide range of weather conditions. This paper presents a new motion detection approach that is based on the Fisher’s linear discriminant-based dual dark channel prior and the cerebellar-model-articulation-controller artificial neural network to completely and accurately detect moving objects in such conditions. The detection results show that our proposed approach is capable of performing with higher efficacy when compared with the results produced by other state-of-the-art approaches in variable bit-rate video streams over changing weather conditions. Both qualitative and quantitative evaluations support this claim; for instance, the proposed approach achieves Similarity and F1 accuracy rates that are 76.40% and 84.37% higher than those of existing approaches, respectively.

並列關鍵字

Automated Motion Detection ； Visibility Restoration ； Intelligent Transportation Systems

參考文獻

[1] N. Buch, S. Velastin, and J. Orwell, “A review of computer vision techniques for the analysis of urban traffic," IEEE Trans. Intelligent Transp. Syst., vol. 12, pp. 920 939, Sept. 2011.

[2] F. C. Cheng, S. C. Huang, and S. J. Ruan, “Tllumination-sensitive background modelling approach for accurate moving object detection," IEEE Trans. on Broadcasting, vol. 57, pp. 794 801, Dec. 2011.

[3] F. C. Cheng, S. C. Huang, and S. J. Ruan, “Scene analysis for object detection in advanced surveillance systems using laplacian distribution model," IEEE Trans. Syst., Man, Cybern. C, Appl. Rev., vol. 41, pp. 589 598, Sept. 2011.

[4] T. Raty, “Survey on contemporary remote surveillance systems for public safety," IEEE Trans. Syst., Man, Cybern. C, Appl. Rev., vol. 40, pp. 493 515, Sept. 2010.

[5] R. T. Collins, A. J. Lipton, and T. Kanade, “Tntroduction to the special section on video surveillance,"

國際替代計量

用於真實世界交通監控系統的高精確度移動物體偵測方法

未授權

主題瀏覽