In order to accurately count the number of animals grazing on grassland, we present a livestock detection algorithm using modified versions of U-net and Google Inception-v4 net. This method works well to detect dense and touching instances. We also introduce a dataset for livestock detection in aerial images, consisting of 89 aerial images collected by quadcopter. Each image has resolution of about 3000 × 4000 pixels, and contains livestock with varying shapes, scales, and orientations. We evaluate our method by comparison against Faster RCNN and Yolo-v3 algorithms using our aerial livestock dataset. The average precision of our method is better than Yolo-v3 and is comparable to Faster RCNN.
Reducing energy consumption has become one of the most important challenges in designing computing systems. Dynamic power management policies exploit components' idle periods to save energy. If one idle period of some component is long enough, the component can be put into low power state during this period in order to reduce energy consumption. Many dynamic power management policies are based on predicting lengths of components' future idle periods. The more accurate the prediction is, the more efficient the policy is. This paper proposes a novel idea of using genetic algorithm to predict lengths of future idle periods. We take K adjacent idle periods and active periods as a load-gene and define some kinds of relationships between adjacent load-genes, then use genetic algorithm to predict future load-genes that most accords with the relationships. Experimental results show that the proposed scheme is more efficient than the exponential-average approach.
H.264/AVC encoder complexity is mainly due to variable block size in Intra and Inter frames. This makes H.264/AVC very difficult to implement, especially for real time applications and mobile devices. The current technological challenge is to conserve the compression capacity and quality that H.264 offers but reduce the encoding time and, therefore, the processing complexity. This paper applies machine learning technique for video encoding mode decisions and investigates ways to improve the process of generating more general low complexity H.264/AVC video encoders. The proposed H.264 encoding method decreases the complexity in the mode decision inside the Inter frames. Results show, on average, a 67.36% reduction in encoding time, a 0.2 dB decrease in PSNR, and an average bit rate increase of 0.05%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.