检索结果-内蒙古大学图书馆

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e.g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e.g., quantisation, pruning, or dedicated lightweight architectures. Due to the logarithmic distribution of weights in neural network layers, a method providing high performance with significant reduction in computational precision (for 4-bit weights and less) is the Power-of-Two (PoT) quantisation (and therefore also with a logarithmic distribution). This method introduces additional possibilities of replacing the typical for neural networks Multiply and ACcumulate (MAC – performing, e.g., convolution operations) units, with more energy-efficient Bitshift and ACcumulate (BAC). In this paper, we show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 SoC FPGA can be at least 1.4x more energy efficient than the uniform quantisation version. To further reduce the actual power requirement by omitting part of the computation for zero weights, we also propose a new pruning method adapted to logarithmic quantisation. © 2022, CC BY.

关键词： System-on-chip

Playing cards and bidding calls detection for automatic registration of a duplicate bridge game

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Wzorek, Piotr Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

In this work, the implementation of a playing cards and bidding calls detection system for the automatic registration of a duplicate bridge game is presented. For this purpose, two YOLOv4 deep convolutional neural networks were used. During the training process, which was carried out using an automatically generated dataset, we obtained a detector characterised by more than 99.9% accuracy on the test set. The prepared system has been evaluated on videos collected during bridge competitions and is characterised by high accuracy. The application has been implemented and evaluated on a CPU and an embedded GPU. © 2022, CC BY.

关键词： Deep neural networks

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

学校读者我要写书评

暂无评论

arXiv 2022年

关键词： System-on-chip

Towards real-time and energy efficient Siamese tracking - a hardware-software approach

学校读者我要写书评

暂无评论

arXiv 2022年

关键词： Energy efficiency

FoundationGrasp: Generalizable Task-Oriented Grasping with Foundation Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Chao Huang, Dehao Dong, Wenlong Xu, Ruinian Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Institute for Robotics and Intelligent Machines Georgia Institute of Technology Atlanta United States

Task-oriented grasping (TOG), which refers to synthesizing grasps on an object that are configurationally compatible with the downstream manipulation task, is the first milestone towards tool manipulation. Analogous to the activation of two brain regions responsible for semantic and geometric reasoning during cognitive processes, modeling the intricate relationship between objects, tasks, and grasps necessitates rich semantic and geometric prior knowledge about these elements. Existing methods typically restrict the prior knowledge to a closed-set scope, limiting their generalization to novel objects and tasks out of the training set. To address such a limitation, we propose FoundationGrasp, a foundation model-based TOG framework that leverages the open-ended knowledge from foundation models to learn generalizable TOG skills. Extensive experiments are conducted on the contributed Language and vision Augmented TaskGrasp (LaViA-TaskGrasp) dataset, demonstrating the superiority of FoundationGrasp over existing methods when generalizing to novel object instances, object classes, and tasks out of the training set. Furthermore, the effectiveness of FoundationGrasp is validated in real-robot grasping and manipulation experiments on a 7-DoF robotic arm. Our code, data, appendix, and video are publicly available at https://***/view/foundationgrasp. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotic arms

Exploring Unstructured Environments using Minimal Sensing on Cooperative Nano-Drones

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Arias-Perez, Pedro Gautam, Alvika Fernandez-Cortizas, Miguel Perez-Saura, David Saripalli, Srikanth Campoy, Pascual The Computer Vision and Aerial Robotics Group Universidad Politécnica de Madrid Spain Spain The Department of Mechanical Engineering Texas A&M University College StationTX United States

Recent advances have improved autonomous navigation and mapping under payload constraints, but current multi-robot inspection algorithms are unsuitable for nano-drones due to their need for heavy sensors and high computational resources. To address these challenges, we introduce ExploreBug, a novel hybrid frontier range bug algorithm designed to handle limited sensing capabilities for a swarm of nano-drones. This system includes three primary components: a mapping subsystem, an exploration subsystem, and a navigation subsystem. Additionally, an intra-swarm collision avoidance system is integrated to prevent collisions between drones. We validate the efficacy of our approach through extensive simulations and real-world exploration experiments involving up to seven drones in simulations and three in real-world settings, across various obstacle configurations and with a maximum navigation speed of 0.75 m/s. Our tests demonstrate that the algorithm efficiently completes exploration tasks, even with minimal sensing, across different swarm sizes and obstacle densities. Furthermore, our frontier allocation heuristic ensures an equal distribution of explored areas and paths traveled by each drone in the swarm. We publicly release the source code of the proposed system to foster further developments in mapping and exploration using autonomous nano drones. Video: https://***/cvarupm/cf-exploration Code: https://***/pariaspe/cf_exploration © 2024, CC BY.

关键词： Mapping

Traffic Sign Classification Using Deep and Quantum Neural Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kuros, Sylwia Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Kraków Poland

Quantum Neural Networks (QNNs) are an emerging technology that can be used in many applications including computer vision. In this paper, we presented a traffic sign classification system implemented using a hybrid quantum-classical convolutional neural network. Experiments on the German Traffic Sign Recognition Benchmark dataset indicate that currently QNN do not outperform classical DCNN (Deep Convolutuional Neural Networks), yet still provide an accuracy of over 90% and are a definitely promising solution for advanced computer vision. © 2022, CC BY.

关键词： Traffic signs

FusionPortableV2: A Unified Multi-Sensor Dataset for Generalized SLAM Across Diverse Platforms and Scalable Environments

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wei, Hexiang Jiao, Jianhao Hu, Xiangcheng Yu, Jingwen Xie, Xupeng Wu, Jin Zhu, Yilong Liu, Yuxuan Wang, Lujia Liu, Ming Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Robot Perception and Learning Lab Department of Computer Science University College London United Kingdom Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China Guangzhou China

Simultaneous Localization and Mapping (SLAM) technology has been widely applied in various robotic scenarios, from rescue operations to autonomous driving. However, the generalization of SLAM algorithms remains a significant challenge, as current datasets often lack scalability in terms of platforms and environments. To address this limitation, we present FusionPortableV2, a multi-sensor SLAM dataset featuring sensor diversity, varied motion patterns, and a wide range of environmental scenarios. Our dataset comprises 27 sequences, spanning over 2.5 hours and collected from four distinct platforms: a handheld suite, a legged robot, a unmanned ground vehicle (UGV), and a vehicle. These sequences cover diverse settings, including buildings, campuses, and urban areas, with a total length of 38.7km. Additionally, the dataset includes ground-truth (GT) trajectories and RGB point cloud maps covering approximately 0.3km2. To validate the utility of our dataset in advancing SLAM research, we assess several state-of-the-art (SOTA) SLAM algorithms. Furthermore, we demonstrate the dataset's broad application beyond traditional SLAM tasks by investigating its potential for monocular depth estimation. The completae dataset, including sensor data, GT, and calibration details, is accessible at https://***/dataset/fusionportable v2. Copyright © 2024, The Authors. All rights reserved.

关键词： SLAM robotics

Traffic Sign Classification Using Deep and Quantum Neural Networks

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Kuros, Sylwia Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Kraków Poland

关键词： Traffic signs