TY  - JOUR
TI  - Elimination of useless images from raw camera-trap data
AB  - Camera-traps are motion triggered cameras that are used to observe animals in nature. The number ofimages collected from camera-traps has increased significantly with the widening use of camera-traps thanks to advancesin digital technology. A great workload is required for wild-life researchers to group and label these images. We proposea system to decrease the amount of time spent by the researchers by eliminating useless images from raw camera-trapdata. These images are too bright, too dark, blurred, or they contain no animals. To eliminate bright, dark, and blurredimages we employ techniques based on image histograms and fast Fourier transform. To eliminate the images withoutanimals, we propose a system combining convolutional neural networks and background subtraction. We experimentallyshow that the proposed approach keeps 99% of photos with animals while eliminating more than 50% of photos withoutanimals. We also present a software prototype that employs developed algorithms to eliminate useless images.
AU  - BAŞTANLAR, Yalın
AU  - TEKELİ, Ulaş
DO  - 10.3906/elk-1808-130
PY  - 2019
JO  - Turkish Journal of Electrical Engineering and Computer Sciences
VL  - 27
IS  - 4
SN  - 1300-0632
SP  - 2395
EP  - 2411
DB  - TRDizin
UR  - http://search/yayin/detay/337141
ER  -