Adaptive Threshold for Background Subtraction in Moving Object Detection using Stationary Wavelet Transforms 2D

Abstract

Abstract-Both detection and tracking objects are challenging problems because of the type of the objects and even their presence in the scene. Generally, object detection is a prerequisite for target tracking, and tracking has no effect on object detection. In this paper, we propose an algorithm to detect and track moving objects automatically of a video sequence analysis, taken with a fixed camera. In the detection steps we perform a background subtraction algorithm, the obtained results are decomposed using discrete stationary wavelet transform 2D and the coefficients are thresholded using Birge-Massart strategy. The tracking step is based on the classical Kalman filter algorithm. This later uses the Kalman filter as many as the number of the moving objects in the image frame. The tests evaluation proved the efficiency of our algorithm for motion detection using adaptive threshold. The comparison results show that the proposed algorithm gives a better performance of detection and tracking than the other methods.

Real‐time reverse osmosis monitoring for antiscalant dose selection in advanced treatment of wastewater

“…Variations of pixel intensities were detected via a background subtraction technique (Zivkovic, 2004; Zivkovic & van der Heijden, 2006), making use of a predefined set of initial (reference) images of the membrane surface to arrive at a background probability density function (PDF) of the intensities for each pixel. During the RO pilot operation, membrane images from the RO membrane monitor were analyzed, and pixel intensities were compared with the background PDF pixel intensities (Boufares, Aloui, & Cherif, 2016). Corrections due to possible variability in illumination were made, relative to the reference image, via the image channel histogram matching technique (Bevilacqua & Azzari, 2007; Shapira, Avidan, & Hel‐Or, 2013), also using a lookup (indexing) algorithm (Bevilacqua & Azzari, 2007; Shapira et al, 2013).…”

“…Indicators: FI, volumetric flow rate. Number of RO elements/vessel: PV-1A/B, four elements; PV-2A/B, three elements; PV-3, three elements; PV-4A, two elements; PV-5A: one element (Boufares, Aloui, & Cherif, 2016). Corrections due to possible variability in illumination were made, relative to the reference image, via the image channel histogram matching technique (Bevilacqua & Azzari, 2007;Shapira, Avidan, & Hel-Or, 2013), also using a lookup (indexing) algorithm (Bevilacqua & Azzari, 2007;Shapira et al, 2013).…”