A Human-Detection Method Based on YOLOv5 and Transfer Learning Using Thermal Image Data from UAV Perspective for Surveillance System

Abstract

At this time, many illegal activities are being been carried out, such as illegal mining, hunting, logging, and forest burning. These things can have a substantial negative impact on the environment. These illegal activities are increasingly rampant because of the limited number of mofficers and the high cost required to monitor them. One possible solution is to create a surveillance system that utilizes artificial intelligence to monitor the area. Unmanned aerial vehicles (UAV) and NVIDIA Jetson modules (general-purpose GPUs) can be inexpensive and efficient because they use few resources. The problem from the object-detection field utilizing the drone’s perspective is that the objects are relatively small compared to the observation space, and there are also illumination and environmental challenges. In this study, we will demonstrate the use of the state-of-the-art object-detection method you only look once (YOLO) v5 using a dataset of visual images taken from a UAV (RGB-image), along with thermal infrared information (TIR), to find poachers. There are seven scenario training methods that we have employed in this research with RGB and thermal infrared data to find the best model that we will deploy on the Jetson Nano module later. The experimental result shows that a new model with pre-trained model transfer learning from the MS COCO dataset can improve YOLOv5 to detect the human–object in the RGBT image dataset.

Deep Learning Model for Unmanned Aerial Vehicle-based Object Detection on Thermal Images

“…Mantau et al [14] demonstrates the utilization of the advanced object-detection technique known as YOLOv5. This method is applied to a dataset comprising visual images captured from a UAV (RGB imagery) combined with TIR for the purpose of poacher detection.…”

Recognizing the rooting action of prepartum sow in free-farrowing pen using computer vision

“…YOLOv5 was employed to detect the sow's head, the trough, the door, and the sow's body with different postures. The network comprises 3 components (Mantau et al, 2022;Redmon et al, 2016): CSP (Connection cross Stage Partial)-Darknet53 as a backbone, SPP (Spatial Pyramid Pooling) and PANet (Path Aggregation Network) in the model neck. The head module processes the aggregated features and generates predictions by analyzing the anchor boxes for object detection.…”

Enhancing UAV Visual Landing Recognition with YOLO’s Object Detection by Onboard Edge Computing

“…Under the combined enhancements of the two technologies, the performance of the GGT-YOLO algorithm for drone-based maritime cruising was improved. In [5], a dataset of visual images taken from a UAV with RGB imaging and thermal infrared information was used for detection. That study employed YOLOv5 as the basic network model and a new model with pre-trained model transfer learning from the MS COCO dataset to improve YOLOv5 for humanobject detection in an RGBT image dataset.…”