Effect of Distance and Light Intensity on Multiple Detection Object

Technological advances in the field of computer vision have begun to be developed, one of which is object detection. Object detection serves to find out information related to the detected object. Many models can be used to detect objects such as Yolo, Resnet and SSD. In object detection, the problems that arise are the distance between the object and the camera and the light intensity. The lower the light intensity, the lower the camera specifications and the further the detection distance will affect the object detection process. This research aims to analyze the detection accuracy and computation under different distance settings and lighting conditions. Based on the experimental results by comparing three models namely Yolo, Resnet and SSD, it can be seen that the best accuracy rate is SSD with an accuracy rate of 98.19%, the decrease in accuracy rate based on the effect of the distance of shooting with the camera occurs in all models while the light intensity that has the best accuracy value is at a low light intensity of 270 Lux. The findings of this study can contribute to improving object detection systems that rely on SSD for applications such as face detection, autonomous driving, surveillance, and traffic monitoring.