Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones

• URL: http://arxiv.org/abs/2402.15273v1
• Date: Fri, 23 Feb 2024 11:35:57 GMT
• Title: Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones
• Authors: Matteo Risso, Francesco Daghero, Beatrice Alessandra Motetti, Daniele Jahier Pagliari, Enrico Macii, Massimo Poncino, and Alessio Burrello
• Abstract summary: Miniaturized unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring. This work proposes a new automatic optimization pipeline for visual pose estimation tasks using Deep Neural Networks (DNNs) Our results improve the state-of-the-art reducing inference latency by up to 3.22x at iso-error.
• Score: 9.806742394395322
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Miniaturized autonomous unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring. Nonetheless, their size and simple electronics pose severe challenges in implementing advanced onboard intelligence. This work proposes a new automatic optimization pipeline for visual pose estimation tasks using Deep Neural Networks (DNNs). The pipeline leverages two different Neural Architecture Search (NAS) algorithms to pursue a vast complexity-driven exploration in the DNNs' architectural space. The obtained networks are then deployed on an off-the-shelf nano-drone equipped with a parallel ultra-low power System-on-Chip leveraging a set of novel software kernels for the efficient fused execution of critical DNN layer sequences. Our results improve the state-of-the-art reducing inference latency by up to 3.22x at iso-error.

Related papers

• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Adaptive Deep Learning for Efficient Visual Pose Estimation aboard Ultra-low-power Nano-drones [5.382126081742012]
  We present a novel adaptive deep learning-based mechanism for the efficient execution of a vision-based human pose estimation task. On a real-world dataset and the actual nano-drone hardware, our best-performing system shows 28% latency reduction while keeping the same mean absolute error (MAE), 3% MAE reduction while being iso-latency, and the absolute peak performance, i.e., 6% better than SoA model.
  arXiv  Detail & Related papers  (2024-01-26T23:04:26Z)
• Quantization-aware Neural Architectural Search for Intrusion Detection [5.010685611319813]
  We present a design methodology that automatically trains and evolves quantized neural network (NN) models that are a thousand times smaller than state-of-the-art NNs. The number of LUTs utilized by this network when deployed to an FPGA is between 2.3x and 8.5x smaller with performance comparable to prior work.
  arXiv  Detail & Related papers  (2023-11-07T18:35:29Z)
• A3D: Adaptive, Accurate, and Autonomous Navigation for Edge-Assisted Drones [12.439787085435661]
  We propose A3D, an edge server assisted drone navigation framework. A3D can reduce end-to-end latency by 28.06% and extend the flight distance by up to 27.28% compared with non-adaptive solutions.
  arXiv  Detail & Related papers  (2023-07-19T10:23:28Z)
• Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs [69.19616451596342]
  Miniaturized unmanned aerial vehicles (UAVs) are an emerging and trending topic. We leverage a novel neural architecture search (NAS) technique to automatically identify several convolutional neural networks (CNNs) for a visual pose estimation task. Our results improve the State-of-the-Art by reducing the in-field control error of 32% while achieving a real-time onboard inference-rate of 10Hz@10mW and 50Hz@90mW.
  arXiv  Detail & Related papers  (2023-03-03T14:02:09Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)
• FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
  This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task. The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources. It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
  arXiv  Detail & Related papers  (2022-01-18T13:59:22Z)
• Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks [61.76338096980383]
  A range of neural architecture search (NAS) techniques are used to automatically learn two types of hyper- parameters of state-of-the-art factored time delay neural networks (TDNNs) These include the DARTS method integrating architecture selection with lattice-free MMI (LF-MMI) TDNN training. Experiments conducted on a 300-hour Switchboard corpus suggest the auto-configured systems consistently outperform the baseline LF-MMI TDNN systems.
  arXiv  Detail & Related papers  (2020-07-17T08:32:11Z)
• DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation [76.90627702089357]
  DepthNet Nano is a compact deep neural network for monocular depth estimation designed using a human machine collaborative design strategy. The proposed DepthNet Nano possesses a highly efficient network architecture, while still achieving comparable performance with state-of-the-art networks.
  arXiv  Detail & Related papers  (2020-04-17T00:41:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.