Just wanted to share a project I recently completed, which utilized the OpenMV H7 Plus to detect vehicles.
Project Links:
The device is an IoT vehicle counter, which can be deployed to monitor any road to count the number of vehicles that drive past it for traffic monitoring purposes.
The OpenMV cam was used to collect a training dataset of images with vehicles, and Edge Impulse was used to train an object detection model with this dataset.
The trained model was uploaded onto the OpenMV Cam, and used to process new images from the device in real-time, to detect when vehicles drove past the device.
I was able to achieve a high accuracy for detections, and it worked at a fast enough frame rate to capture vehicles as they drove by. (Frame rate in gif is slower than actual cam framerate)
I’ve worked with the OpenMV Cam and Edge Impulse now for a few projects, and am always impressed by how well they operate together.