Motion Blur Detection With an Indicator Function for Surveillance Machines

Abstract

Motion is an important clue for industrial inspection, video surveillance, and service machines to localize and recognize products and objects. Because blur cooccurs with motion, it is desirable for developing efficient and robust motion blur detection algorithm. However, existing algorithms are in-efficient for detecting spatial-varying motion blur. To deal with the problem, this paper presents a theorem according to which motion blur can be efficiently detected and segmented. According to the Theorem, the proposed algorithm requires a simple filtering operation and variance computation. Classification as either blurred or un-blurred pixel can be done by substituting the variance into the proposed simple formula and checking the sign of the resulting value. Moreover, a geometric interpretation and two extensions of the algorithm are given. Importantly, based on the geometric interpretation of the indicator function, we develop a one-class classifier which is more effective than the indicator function and has comparable computational cost of the indicator function. Experimental results on detecting motion-blurred cars, motorcycles, bicycles, bags, and persons demonstrate that the proposed algorithm is very efficient without loss of effectiveness.

Video Object Detection Guided by Object Blur Evaluation

“…The first representative dataset for blur mapping was proposed by Shi et al [30], and it contained two types of blur: motion blur and out-of-focus. The subsequent blur mapping methods focused on either the out-of-focus [31] or the motion blur [32]. The most existing blur mapping algorithms were based on hand-craft features, thus they were not robust enough to discriminate the truly blur region and the flat region in the nature such as the sky.…”

Blur parameter locus curve and its applications

“…However, the effect of downsampling on defocus blur has not been discussed. Pang et al [13, 14] used directional filter responses for distinguishing between motion blur and defocus blur. These methods highlight the importance of the use of PSF characteristics.…”

Effective pixel classification of Mars images based on ant colony optimization feature selection and extreme learning machine

“…In addition, these images are blurred by instrument movement and are contaminated by environment noise. In [4], a theorem for the efficient segmentation and detection of motion blur was presented which led to the classification of pixels as either blurred or unblurred. Furthermore, in [5], a new kernel-specific feature vector with a good discrimination property was proposed and then presented for the classifiers to detect different types of blur including motion and defocus blurs.…”