Crowd Estimation Using Histogram Model ClassificationBased on Improved Uniform Local Binary Pattern

Abstract

Abstract-Estimating crowd density may be a good solution for control management, maintaining the crowd safety, or prevention of riot and high risk activities. This paper presents a computational fast and simple method for estimating crowd density based on histogram model classification. The histogram model here is based on the proposed Improved Uniform Local Binary Pattern features. Two main advantages of using this improved version of the local binary pattern are that the pattern features are now intensity invariant as well as rotational invariant. Our proposed method also uses less number of features which makes it faster without sacrificing the overall performance. It has been shown that this method is robust in areas with very low, low, and medium crowd densities. Performance and comparisons with the original local binary pattern method are demonstrated in experimental results.

COVID-19 Diagnosis: ULGFBP-ResNet51 approach on the CT and the Chest X-ray Images Classification

“…LBP is one of the most efficient texture descriptors which has been exerted in many feature extraction and processing tasks [16,[36][37][38][39][40][41][42][43][44]. In [6], they apply the same feature extraction method on X-ray images for COVID-19 identification.…”

“…The ULBP histogram concatenates regions histogram as the global feature vector (see part (e) in Figure 3). The short feature vector and never changing on rotation are the main advantages of this method [38,39]. Mathematically, ULBP and its histogram are:…”