One of the most difficult tasks in the area of computer vision is object detection, which combines object categorization and object location within a scene. In terms of object detection, Deep Neural Networks have been recently demonstrated to outperform alternative approaches. The issues related deep learning neural network is its complexity and huge computation, so it is not possible to detect and track the objects in image of high resolution in real time. We proposed scaled YOLOv4 lite model as Single Stage Detector Neural Network for object detection, tracking and it is trained using COCO 2017 dataset. To create the YOLOv4-CSP- P5- P6- P7- P8 networks, the Scaled YOLOv4 applied efficient network scaling strategies. The additional layer in YOLOv4 lite model is added as P8 layer which improves accuracy. Cross-stage-partial (CSP) connections and Mish activation are used in improved network design, such as backbone optimization and Neck (PAN). In the case of YOLOv4, however, it can only be trained once for all resolutions. Width and Height activations have been changed, allowing for faster network training. With YOLOv4 lite model, we used CSPDarkNet-53 model as a backbone. The experimental result show our YOLOv4 lite model can detect and track object up to 28 fps when model run with the video input and has an accuracy of 86.09% when tested on real-time video with resolutions 1920 × 1080 (full HD). AP = 50.81%, AP @50 = 63.6%, and AP @75 = 52.5% for CSPDarkNet-53 model backbone.

/pdf/object-classification-and-tracking-using-scaled-p8-yolov4-2ncwly4x.pdf

Object Classification and Tracking Using Scaled P8 YOLOv4 Lite Model

This paper illustrates the deployment of the background subtraction (BGS) approach in detecting and tracking the targeted moving objects (MOs). Through the BGS method, there is a potential of cost-saving because the process of storing data occurs once the motion is detected. The aim was to detect the MOs effectively. The applied technique is applicable at all scenarios and places that need the real-time video surveillance systems (VSS), including airports, forest, frequent entrances for criminals, traffic monitoring, country borders, cash machines, schools, banks, among other challenging outdoor and indoor areas. The concept of installing VSS is substantially much needed. The BGS method was employed with fewer complications so that the approach can be utilised in a pragmatic manner (conditions) where the VSS is highly needed. The VSS must be more convenient, effective and efficient to enhance advanced security systems. © 2020 Published by Faculty of Engineeringg

/pdf/deploying-background-subtraction-approach-for-tracking-and-fi42siu2it.pdf

Garima Devpriya

Papers

Deploying background subtraction approach for tracking and detecting moving objects