Nguyen, Thanh Binh
(School of Electronics Engineering, Soongsil University)
,
Chung, Sun-Tae
(School of Electronics Engineering, Soongsil University)
,
Kim, Yu-Sung
(School of Electronics and Electrical Engineering, Hongik Univ.)
,
Kim, Jae-Min
(School of Electronics and Electrical Engineering, Hongik Univ.)
Accompanied by the rapid development of Computer Vision, Visual surveillance has achieved great evolution with more and more complicated processing. However there are still many problems to be resolved for robust and reliable visual surveillance, and the cast shadow occurring in motion detection pro...
Accompanied by the rapid development of Computer Vision, Visual surveillance has achieved great evolution with more and more complicated processing. However there are still many problems to be resolved for robust and reliable visual surveillance, and the cast shadow occurring in motion detection process is one of them. Shadow pixels are often misclassified as object pixels so that they cause errors in localization, segmentation, tracking and classification of objects. This paper proposes a novel cast shadow removal method. As opposed to previous conventional methods, which considers pixel properties like intensity properties, color distortion, HSV color system, and etc., the proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the background scene. Then, the product of the outcomes of application determines whether the blob pixels in the foreground mask comes from object blob regions or shadow regions. The proposed method is simple but turns out practically very effective for Gaussian Mixture Model, which is verified through experiments.
Accompanied by the rapid development of Computer Vision, Visual surveillance has achieved great evolution with more and more complicated processing. However there are still many problems to be resolved for robust and reliable visual surveillance, and the cast shadow occurring in motion detection process is one of them. Shadow pixels are often misclassified as object pixels so that they cause errors in localization, segmentation, tracking and classification of objects. This paper proposes a novel cast shadow removal method. As opposed to previous conventional methods, which considers pixel properties like intensity properties, color distortion, HSV color system, and etc., the proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the background scene. Then, the product of the outcomes of application determines whether the blob pixels in the foreground mask comes from object blob regions or shadow regions. The proposed method is simple but turns out practically very effective for Gaussian Mixture Model, which is verified through experiments.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
제안 방법
However, it cannot deal with shadows and fast illumination changes [8]. In this paper, we propose a cast shadow removing method which can correct the blob region result of GMM. In [6], Stauffer and Grimson model the RGB value history by a mixture of K Gaussian distributions, while, in our paper, we use the K Gaussian distributions to Model for just the Y element in YUV format.
In order to see the effectiveness of the proposed cast shadow removal method in this paper, we conduct experiments which compare between status before and after applying the proposed method in three different types of scenes such as highway, indoor car parking lot and playground. Fig.
In this paper, we proposed a simple but effective cast shadow removal method. The proposed method applies the Laplacian edge detector to each pixel in blob regions in the in the current frame and the background scene, and from the product of the outcomes of application, determine whether the blob pixels in the foreground mask comes from object blob regions or shadow regions. Then, product of the outcomes of application determines whether the pixels in the foreground mask comes from object blob regions or shadow regions.
이론/모형
In this paper, we propose a simple but effective cast shadow removal method for blobs in Gaussian Mixture Model (GMM) [6] in the context of gray scale video. By distinguishing edge detection filtering with selected pixels and suitable neighbors on scene frame data and background, we can extract blobs without cast shadow.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.