As cities and towns embark on a speedy development drive at the expense of their valuable green cover, researchers from Hyderabad’s Indian Institute of Information Technology (IIIT) have created a system that would allow them to scientifically count trees and produce density maps. All that is necessary to produce a tree count and density map is to ride across the city with only a fundamental camera that will record videos and reveal the outcome inside minutes.
The laptop or computer-vision-aided tool for object detection functions on the basis of a machine-studying algorithm, which automatically detects and counts the trees. It then generates a colour-coded map of the city to highlight the extent of tree cover along routes. Arpit Bahety, a 23-year-old investigation fellow at the institute’s Center for Visual Information Technology lab, tested the tool working with footage from a GoPro camera that was mounted on a helmet on the back seat of his scooter. A equivalent experiment was carried out in Gujarat’s Surat as properly, this time working with footage from a Samsung mobile phone. The technique managed an 83 per cent accuracy for the duration of the trials in these two cities.
The researchers created a machine studying model, which can detect trees at when. This platform also avoids duplication, a typical error when numerous trees are manually counted. Speaking to Indian Express Online, Bahety mentioned the camera can be mounted on any car and it will detect tress. The only catch is that the camera has to be facing left. The camera will detect the tree based on the trunk. The video is then fed into a technique that generates a map, enabling them to know the green cover of various places. Over 50 trees a kilometre would be deemed a great count, although something decrease than 20 would be low. The map denotes places of great tree count with dark green these with a low count in black.
The group now hopes to employ the technique in various cities to fully grasp the model’s big-scale efficacy. It believes the tool could also aid assess urban afforestation efforts.