Intelligent video surveillance using enhanced deep belief based multilayered convolution neural network classification techniques

Abstract

Video surveillance has undergone numerous changes in the past few years and several pieces of research have been carried out in this field. Object tracking is the significant task in such systems, and hence it is essential to review the standard approaches dealing with object detection, classification and tracking. This work proposes a novel classification technique for a detected object of a moving scene from a video dataset. Initially the dataset has been processed and prepared for data training based on neural networks. The data has been classified using the proposed enhanced deep belief based multilayered convolutional neural network (EBMCNN). The major focus is on deep learning applications involved in estimating the count, total persons involved and the activities in a crowd where all criteria are taken into consideration, thereby achieving security through video analysis. Identifying theft and the detection of violence are some security measures where video is converted to frames which are then processed to analyse the individuals along with their activities. The classification is performed through comparative analysis of a real‐time dataset. Experimental results show the accuracy 97%, precision 93.8%, recall 87.7% and F‐1 score 87.5%.

Image convolution techniques integrated with YOLOv3 algorithm in motion object data filtering and detection

“…A review of past research literature reveals that many researchers have conducted studies in this area. Kaliappan et al 5 proposed a novel classification technique for detecting objects in motion scenes from video datasets. They employed an enhanced deep belief-based multilayer CNN for data classification, achieving a recognition accuracy of 97% and demonstrating good results 5 .…”

“…Kaliappan et al 5 proposed a novel classification technique for detecting objects in motion scenes from video datasets. They employed an enhanced deep belief-based multilayer CNN for data classification, achieving a recognition accuracy of 97% and demonstrating good results 5 . In their research, Shen et al 6 presented an image enhancement algorithm based on DL for video surveillance scenes.…”

Small object detection leveraging density‐aware scale adaptation

“…These well‐known detectors perform effectively on natural images (e.g., MS COCO (Lin et al, 2014) and Pascal VOC (Everingham et al, 2010)). However, in satellite‐based (or UAV‐based) surveillance (Kaliappan et al, 2022), search and rescue (Balasundaram & Krishnamoorthy, 2022), and military reconnaissance tasks where the targets are migrated to small instances, the performance of small object detection is still far from satisfactory for mainly three challenges, as shown in Figure 1: (1) small size with limited details, rendering the task of distinguishing targets from the background fairly difficult; (2) occlusion with ambiguous boundaries, leading to poor localisation; (3) variant scales with feature inconsistency, resulting in biased detection results for targets with different scales in the same scene. Therefore, small object detection, especially in densely distributed situations of remote sensing scenes, remains an open and challenging problem, requiring urgent efforts.…”

High‐resolution optical remote sensing image change detection based on dense connection and attention feature fusion network

“…Recently, with the development of computing resources (such as graphics processing unit (GPU)) and big data, deep learning technology has been widely used in various areas. Due to its powerful feature representation and non‐linear problem modelling ability, deep learning has made remarkable achievements in computer vision (CV) (Canziani et al, 2016), such as object detection (Fang, Liao, et al, 2021), video surveillance (Kaliappan et al, 2022) and image restoration (Xu et al, 2022). Excitedly, it has also been gradually expanded to the remote sensing field, including segmentation of images (Wang et al, 2021) and point clouds (Zhang & Fan, 2022), image matching (Albanwan & Qin, 2022) and image denoising (Huang et al, 2022), etc.…”