Convolutional Neural Networks (CNNs), are nowadays present in many different embedded solutions. One of the biggest problems related to their execution is the memory bottleneck. In this work we propose an optimal double buffering tiling strategy, to reduce the memory bandwidth in the execution of deep CNN architecture, testing our model on one of the two cores of a Zynq®-7020 embedded platform. An optimal tiling strategy is found for each layer of the network, optimizing for lowest external memory On-Chip memory bandwidth. Performance test results show an improvement in the total execution time of 50% (cache disabled / 34% cache enabled), compared to a non double buffered implementation. Moreover, a 5x lower external memory On-Chip memory double buffering memory bandwidth is achieved, with respect to naive tiling settings. Furthermore it is shown that tiling settings for highest OCM usage do not generally lead to the lowest bandwidth scenario.
State-of-the-art solutions to optical flow fail to jointly offer high density flow estimation, low power consumption and real time operation, rendering them unsuitable for embedded applications. Joint hardware-software scalability at run-time is crucial to achieve these conflicting requirements in one device. This paper therefore presents a scalable Lucas-Kanade optical flow algorithm, together with a flexible power-optimized processor architecture. The C-programmable processor exploits algorithmic scalability through innovations in its memory structure, memory interface, and datapath optimized for efficient convolutions. Jointly, the scalable flow algorithm and optimized computer vision hardware platform enable applications to on-the-fly tradeoff throughput and power consumption in function of flow density and accuracy. The processor chip is synthesized in 40nm CMOS technology and verified on FPGA. The architecture is capable of scaling the frame rate at run-time and processes 16fps of dense optical flow at 640×480 resolution with 15.06 • average angular error, while only consuming 24mW.
Problems with aphids in small grain cereals, either direct by feeding, or indirect by transmission of Barley Yellow Dwarf Virus, are expected to increase due to climate change and a recent ban on neonicotinoid seed treatments by the European Union. Moreover, insecticide resistance against pyrethroid insecticides is reported at multiple locations throughout the world. Therefore, a better understanding of cereal aphid population dynamics and increased attention towards an integrated pest management is needed. In this study, cereal aphids were monitored on 193 maize and small grain cereal fields throughout Flanders, Belgium. The population dynamics and species distribution were observed throughout the year and the effects of spatio-temporal variables were explored. A significant negative effect was found of grassland in a 1,000 m radius and a positive effect of grain maize in a 3,000 m radius around a small grain cereals field on the maximum infestation rate with aphids in autumn within this field. In a 3,000 m and 5,000 m radius, a significant positive effect of grain maize and a significant negative effect of other small grain cereals was found on the maximum infestation rate during the whole growing season within this field. The mean daily average temperature from 118 to 19 d before sowing had a significant positive effect on the maximum infestation rate in autumn. Mean precipitation, wind speed, and humidity from 52 to 26, 46 to 23, and 107 to 13 d before sowing respectively, had a significant negative effect on the maximum infestation rate in autumn.
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.