Reliable Recognition of Partially Occluded Objects with Correlation Filters

Abstract

Design of conventional correlation filters requires explicit knowledge of the appearance and shape of a target object, so the performance of correlation filters is significantly affected by changes in the appearance of the object in the input scene. In particular, the performance of correlation filters worsens when objects to be recognized are partially occluded by other objects, and the input scene contains a cluttered background and noise. In this paper, we propose a new algorithm for the design of a system consisting of a set of adaptive correlation filters for recognition of partially occluded objects in noisy scenes. Since the input scene may contain different fragments of the target, false objects, and background to be rejected, the system is designed in such a manner to guarantee equally high correlation peaks corresponding to parts of the target in the scenes. The key points of the system are as follows: (i) it consists of a bank of composite optimum filters, which yield the best performance for different parts of the target; (ii) it includes a fragmentation of the target into a given number of parts in the training stage to provide equal intensity responses of the system for each part of the target. With the help of computer simulation, the performance of the proposed algorithm for recognition partially occluded objects is compared with that of common algorithms in terms of objective metrics.

Target Field of View Prediction Using Artificial Pheromones for People Reidentification

“…Correlation filters (CF) are used in pattern recognition due to following advantages [20], [27], [45], [46]: a) invariant to noise, shift, and variable illumination, b) high ability for discrimination, c) ability to use both content and shape, d) can simultaneously detect and locate, and e) ability to continually adapt to changes in appearance. Correlation filters can be applied to face detection [47], [48], tracking [49]- [51] and recognition [52].…”

Pose Estimation in Noncontinuous Video Sequences Using Evolutionary Correlation Filtering

“…Conventionally, the design of correlation filters requires an explicit knowledge of the appearance and shape of the target [12]. An effective design strategy consists of the construction of a set of correlation filters, in which each filter is modeled with each possible appearance version of the target that is expected in the observed scene [12]. Thus, this approach allows us to recognize several geometrically modified versions of the target.…”