TY - GEN
T1 - A case study of object recognition from drone videos
AU - Fortes, Stacy
AU - Kulesza, Robert
AU - Li, J. Jenny
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/3
Y1 - 2021/3
N2 - To study a potential autonomous drone's object recognition and reaction, we created a convolutional neural network (CNN) and used it to detect and count the empty parking spots in a parking lot taken from drone video footage. We first trained the network through supervised learning with snapshots of individual parking spots, from a previous drone footage, to correctly classify the spots as empty or occupied. Then we store the model to be used for detection and labeling of objects in new drone videos such as empty vs. occupied spots, as well as cars moving in and out of spots. We invented a video object referencing (VOR) to estimate object dimensions. After many rounds of tuning, we eventually achieve close to a hundred percent of accuracy. We concluded that adjusting batch size and epoch number could improve object recognition. We hope this research will contribute to tuning CNN for object recognition from drone videos to help with eventual autonomous drones.
AB - To study a potential autonomous drone's object recognition and reaction, we created a convolutional neural network (CNN) and used it to detect and count the empty parking spots in a parking lot taken from drone video footage. We first trained the network through supervised learning with snapshots of individual parking spots, from a previous drone footage, to correctly classify the spots as empty or occupied. Then we store the model to be used for detection and labeling of objects in new drone videos such as empty vs. occupied spots, as well as cars moving in and out of spots. We invented a video object referencing (VOR) to estimate object dimensions. After many rounds of tuning, we eventually achieve close to a hundred percent of accuracy. We concluded that adjusting batch size and epoch number could improve object recognition. We hope this research will contribute to tuning CNN for object recognition from drone videos to help with eventual autonomous drones.
KW - Accuracy
KW - Convolutional Neural Networks (CNN)
KW - Object Recognition
KW - TensorFlow
UR - http://www.scopus.com/inward/record.url?scp=85111352358&partnerID=8YFLogxK
U2 - 10.1109/ICICT52872.2021.00021
DO - 10.1109/ICICT52872.2021.00021
M3 - Conference contribution
AN - SCOPUS:85111352358
T3 - Proceedings - 2021 4th International Conference on Information and Computer Technologies, ICICT 2021
SP - 84
EP - 87
BT - Proceedings - 2021 4th International Conference on Information and Computer Technologies, ICICT 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference on Information and Computer Technologies, ICICT 2021
Y2 - 11 March 2021 through 14 March 2021
ER -