<![CDATA[Vehicle counting systems using image processing and deep learning have been widely studied. Using images captured by CCTV cameras makes vehicle counting effective and efficient. Although much research has been done, there are still challenges in direct application in the field. Object detection methods such as YOLO are widely chosen. In field applications, challenges are found such as rainy, nighttime, or foggy conditions and the use of appropriate hardware. In this study, the YOLOv8s and YOLOv8n object detection methods are proposed using contrast-limited Adaptive Histogram Equalization (CLAHE) image enhancement in preprocessing and datasets and run using SBC Jetson Nano. From this study, the results obtained an increase in detection values of around 10% to 20% in dark image conditions and there was no improvement for bright images. The average accuracy is 0.873312 for YOLOv8s and 0.866906 for YOLOv8n with image enhancement. And the processing time on Jetson Nano is 59.5 ms for YOLOv8n.]]>
