This paper proposes a supervised classification approach for the real-time pattern recognition of sows in an animal supervision system(asup).Our approach offers the possibility of the foreground subtraction in an asup...
详细信息
This paper proposes a supervised classification approach for the real-time pattern recognition of sows in an animal supervision system(asup).Our approach offers the possibility of the foreground subtraction in an asup’s imageprocessing module where there is lack of statistical information regarding the background.A set of 7 farrowing sessions of sows,during day and night,have been captured(approximately 7 days/sow),which is used for this *** frames of these recordings have been grabbed with a time shift of 20 s.A collection of 215 frames of 7 different sows with the same lighting condition have been marked and used as the training *** on small neighborhoods around a point,a number of image local features are defined,and their separability and performance metrics are *** the classification task,a feed-forward neural network(NN)is studied and a realistic configuration in terms of an acceptable level of accuracy and computation time is *** results show that the dense neighborhood feature(d.3×3)is the smallest local set of features with an acceptable level of separability,while it has no negative effect on the complexity of *** results also confirm that a significant amount of the desired pattern is accurately detected,even in situations where a portion of the body of a sow is covered by the crate’s *** performance of the proposed feature set coupled with our chosen configuration reached the rate of 8.5 *** true positive rate(TPR)of the classifier is 84.6%,while the false negative rate(FNR)is only about 3%.A comparison between linear logistic regression and NN shows the highly non-linear nature of our proposed set of features.
The detection and control of larval habitats -in particular, temporary water bodies- can play an important role in fighting against mosquito-transmitted diseases like malaria. In this paper, we explore the feasibility...
详细信息
ISBN:
(纸本)9781665461719
The detection and control of larval habitats -in particular, temporary water bodies- can play an important role in fighting against mosquito-transmitted diseases like malaria. In this paper, we explore the feasibility of identifying temporary water bodies from images taken by surveillance drones at realtime using the YOLOv4 algorithm. For our experiments, we use a dataset consisting of 782 drone-captured images, which includes 1522 temporary water bodies of different sizes and shapes, including puddles (i.e., small accumulations of water on a surface). Although still preliminary, our results are encouraging: the YOLOv4 trained models obtained a general score of 71.47(6.42)% mAP, and the processingtime per image is 24:87 milliseconds, on average. In terms of size, the models can identify puddle objects as small as 23x23 cm on images taken from 120 m over surface-level.
OpenCV is a growing technology, and it has the potential to replace the current technologies used in security systems, space applications, hospitals etc. This paper proposes the use of OpenCV's image-processing fe...
详细信息
ISBN:
(纸本)9781538605691
OpenCV is a growing technology, and it has the potential to replace the current technologies used in security systems, space applications, hospitals etc. This paper proposes the use of OpenCV's image-processing feature embedded in an automated robot, which can be used in hospitals and such. Hospitals often require the monitoring of patients at regular intervals, coupled with administering the prescribed medications according to a particular schedule. The proposed robot system can be significantly helpful at hospitals where the number of nurses are not enough to take care of all the patients. Owing to people's forgetfulness due to age and other aspects, they may miss their medication meant to be taken at a specific time. This delay can further deteriorate the health of the patient. The automated robot system analyses the position of each bed and matches the medicine intake using imageprocessing concepts, ensuring that the patient takes his/her dosage according to the schedule specified by the doctor.
暂无评论