Embedded Computer Vision for Agricultural Applications

Computer vision has been one of the fields that has had more researched done in the Deep Learning than any other field due to the possibilities it carries. This can be seen by just looking at the amount of different object detection algorithms implemented in many different fields such as manufacturing, medical, autonomous driving, agriculture, etc. The next step could be made in the direction of an embedded system, starting with microcomputers, this considers the progress companies are making in hardware capabilities and reduction of costs and size, where a microcomputer that fits in your hand, making it portable and easy to move around and adapt to different settings. The hardware capabilities of this small devices have achieved similar performances as low budget laptops and personal computers, however the price of most of this hardware systems are lower than a laptop or a PC. This chapter presents how the implementation of deep learning object detection techniques in said systems could help not only big agriculture producers, but also small local producers and even personal greenhouses. This is done by presenting the advances done in agriculture by using object detectors and the possibilities given by different microcomputers and the steps required to mash the two technologies together into an embedded future. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Embedded Computer Vision for Agricultural Applications Chapter in Scopus