Combining where and what in change detection for unsupervised foreground learning in surveillance

Abstract

Change detection is the most important task for video surveillance analytics such as foreground and anomaly detection. Current foreground detectors learn models from annotated images since the goal is to generate a robust foreground model able to detect changes in all possible scenarios. Unfortunately, manual labelling is very expensive. Most advanced supervised learning techniques based on generic object detection datasets currently exhibit very poor performance when applied to surveillance datasets because of the unconstrained nature of such environments in terms of types and appearances of objects. In this paper, we take advantage of change detection for training multiple foreground detectors in an unsupervised manner. We use statistical learning techniques which exploit the use of latent parameters for selecting the best foreground model parameters for a given scenario. In essence, the main novelty of our proposed approach is to combine the where (motion segmentation) and what (learning procedure) in change detection in Preprint submitted to Pattern Recognition November 3, 2014 an unsupervised way for improving the specificity and generalization power of foreground detectors at the same time. We propose a framework based on latent Support Vector Machines that, given a noisy initialization based on motion cues, learns the correct position, aspect ratio, and appearance of all moving objects in a particular scene. Specificity is achieved by learning the particular change detections of a given scenario, and generalization is guaranteed since our method can be applied to any possible scene and foreground object, as demonstrated in the experimental results outperforming the state-of-the-art.

Learning Scene-specific Object Detectors Based on a Generative-Discriminative Model with Minimal Supervision

“…Other than the above mentioned approaches, there exist methods [54,55] to detect unknown object classes from the motion segmentation. Although these methods learn foreground models in arbitrary scenarios without any a priori assumption, they are very different from our method, which address one object category detection problem: these methods can not recognize the detected responses because they use the cluster based global optimization procedure.…”

Motion-region annotation for complex videos via label propagation across occluders

“…Motion analysis is a prerequisite in video analysis with its applications in computer vision ranging from surveillance [1][2][3], multi-object tracking and crowd estimation [4][5][6][7][8][9] to gesture recognition [10,11], video object segmentation [12][13][14][15][16][17], behavior analysis [18,19] and anomaly detection [20][21][22]. An objective analysis of moving objects can be carried out when motion is accurately detected and segmented as a prior.…”

Assessment of Data Fusion Algorithms for Earth Observation Change Detection Processes

“…Determining changed areas in images of the same scene taken at different points in time is of considerable interest given that it offers a large number of applications in various disciplines [2], including: video-surveillance [3], medical diagnoses and treatment [4], vehicle driving support [5] and remote detection.…”