Image classification and segmentation for efficient surveillance applications / Maryam Asadzadeh Kaljahi

• Main Author: Maryam Asadzadeh, Kaljahi
• Format: Thesis
• Published: 2019
• Subjects: QA75 Electronic computers. Computer science; QA76 Computer software
• Online Access: http://studentsrepo.um.edu.my/11598/1/Maryam_Asadzadeh.pdf; http://studentsrepo.um.edu.my/11598/2/Maryam.pdf; http://studentsrepo.um.edu.my/11598/

Image or video-based surveillance systems are playing a vital role in developing smart city and disaster management, such as flood and air pollution, etc. The need for the above surveillance systems is increasing exponentially. As a result, there is a demand for developing an accurate, efficient and safe system. There are existing systems for solving the above issues but the performance of the systems degrades or inconsistent for the different applications and situations. Besides, most existing systems do not aim to combine image processing and networking as one system for addressing the challenges. Therefore, there is immense scope for developing a new image-based surveillance system, which can cope with the causes of different applications and situations with minimum changes. To address the above research challenge, the proposed work is divided into three sub-challenges, namely, classification of images for developing a generalized system, segmentation for image size reduction and detecting region for safe landing for the purpose of safety. To solve the above challenge-1, in the past, the methods are developed, which include content-based image retrieval, scene categorization, and deep learning-based. The main issue of these methods is that the methods are limited to particular shapes of the objects in the images. In the same way, deep learning-based methods expect a large number of labeled samples and high computations. Therefore, the methods are limited to specific classification but not the classification considered in this work, which requires the generalized method. Thus, the proposed work aims at developing a new method for extracting edge strength and sharpness for classification of different image classes namely, soil, flood, air pollution, plant growth and garbage scene images. The reason to choose the above features is that these features can be used to extract unique observation in the images irrespective of objects shape. To address the challenge-2, edge, texture, color and deep learning-based methods are proposed in the past. However, the methods are sensitive to background complexity and may not work well for the proposed image classes because each image can contain multiple colors, texture, etc. Therefore, the proposed work introduces a general saliency-based method for segmenting common region of the images. To find a solution to the above challenge-3, the existing methods extract texture, edges, and color for detecting flat region (safe landing zone) in the images. However, these methods are not adequate for the proposed images of complex background. Hence, the proposed work explores Gabor orientation responses for studying flat and rough region instead of magnitude values. The developed methods would be evaluated on different datasets to validate their performance.