Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization

• URL: http://arxiv.org/abs/2108.08166v1
• Date: Wed, 18 Aug 2021 14:21:53 GMT
• Title: Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization
• Authors: Lukas St\"acker, Juncong Fei, Philipp Heidenreich, Frank Bonarens, Jason Rambach, Didier Stricker, and Christoph Stiller
• Abstract summary: We consider the deployment of two representative object detection networks on an edge AI platform. In particular, we consider RetinaNet for image-based 2D object detection and PointPillars for LiDAR-based 3D object detection. We evaluate the runtime of the deployed algorithms using two different libraries,RT and TorchScript.
• Score: 11.408144862469172
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deep neural networks have proven increasingly important for automotive scene understanding with new algorithms offering constant improvements of the detection performance. However, there is little emphasis on experiences and needs for deployment in embedded environments. We therefore perform a case study of the deployment of two representative object detection networks on an edge AI platform. In particular, we consider RetinaNet for image-based 2D object detection and PointPillars for LiDAR-based 3D object detection. We describe the modifications necessary to convert the algorithms from a PyTorch training environment to the deployment environment taking into account the available tools. We evaluate the runtime of the deployed DNN using two different libraries, TensorRT and TorchScript. In our experiments, we observe slight advantages of TensorRT for convolutional layers and TorchScript for fully connected layers. We also study the trade-off between runtime and performance, when selecting an optimized setup for deployment, and observe that quantization significantly reduces the runtime while having only little impact on the detection performance.

Related papers

• EfficientCD: A New Strategy For Change Detection Based With Bi-temporal Layers Exchanged [3.3885253104046993]
  We propose a novel deep learning framework named EfficientCD for remote sensing image change detection. The framework employs EfficientNet as its backbone network for feature extraction. The EfficientCD has been experimentally validated on four remote sensing datasets.
  arXiv  Detail & Related papers  (2024-07-22T19:11:50Z)
• A Point-Based Approach to Efficient LiDAR Multi-Task Perception [49.91741677556553]
  PAttFormer is an efficient multi-task architecture for joint semantic segmentation and object detection in point clouds. Unlike other LiDAR-based multi-task architectures, our proposed PAttFormer does not require separate feature encoders for task-specific point cloud representations. Our evaluations show substantial gains from multi-task learning, improving LiDAR semantic segmentation by +1.7% in mIou and 3D object detection by +1.7% in mAP.
  arXiv  Detail & Related papers  (2024-04-19T11:24:34Z)
• ELGC-Net: Efficient Local-Global Context Aggregation for Remote Sensing Change Detection [65.59969454655996]
  We propose an efficient change detection framework, ELGC-Net, which leverages rich contextual information to precisely estimate change regions. Our proposed ELGC-Net sets a new state-of-the-art performance in remote sensing change detection benchmarks. We also introduce ELGC-Net-LW, a lighter variant with significantly reduced computational complexity, suitable for resource-constrained settings.
  arXiv  Detail & Related papers  (2024-03-26T17:46:25Z)
• AOP-Net: All-in-One Perception Network for Joint LiDAR-based 3D Object Detection and Panoptic Segmentation [9.513467995188634]
  AOP-Net is a LiDAR-based multi-task framework that combines 3D object detection and panoptic segmentation. The AOP-Net achieves state-of-the-art performance for published works on the nuScenes benchmark for both 3D object detection and panoptic segmentation tasks.
  arXiv  Detail & Related papers  (2023-02-02T05:31:53Z)
• Anytime-Lidar: Deadline-aware 3D Object Detection [5.491655566898372]
  We propose a scheduling algorithm, which intelligently selects the subset of the components to make effective time and accuracy trade-off on the fly. We apply our approach to a state-of-art 3D object detection network, PointPillars, and evaluate its performance on Jetson Xavier AGX dataset.
  arXiv  Detail & Related papers  (2022-08-25T16:07:10Z)
• AGO-Net: Association-Guided 3D Point Cloud Object Detection Network [86.10213302724085]
  We propose a novel 3D detection framework that associates intact features for objects via domain adaptation. We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
  arXiv  Detail & Related papers  (2022-08-24T16:54:38Z)
• A Single-Target License Plate Detection with Attention [56.83051142257412]
  Neural Network is commonly adopted to the License Plate Detection (LPD) task and achieves much better performance and precision, especially CNN-based networks can achieve state of the art RetinaNet. For a single object detection task such as LPD, modified general object detection would be time-consuming, unable to cope with complex scenarios and a cumbersome weights file that is too hard to deploy on the embedded device.
  arXiv  Detail & Related papers  (2021-12-12T03:00:03Z)
• Edge-Detect: Edge-centric Network Intrusion Detection using Deep Neural Network [0.0]
  Edge nodes are crucial for detection against multitudes of cyber attacks on Internet-of-Things endpoints. We develop a novel light, fast and accurate 'Edge-Detect' model, which detects Denial of Service attack on edge nodes using DLM techniques.
  arXiv  Detail & Related papers  (2021-02-03T04:24:34Z)
• PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection [100.60209139039472]
  We propose the PointVoxel Region based Convolution Neural Networks (PVRCNNs) for accurate 3D detection from point clouds. Our proposed PV-RCNNs significantly outperform previous state-of-the-art 3D detection methods on both the Open dataset and the highly-competitive KITTI benchmark.
  arXiv  Detail & Related papers  (2021-01-31T14:51:49Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)
• Optimisation of the PointPillars network for 3D object detection in point clouds [1.1470070927586016]
  In this paper we present our research on the optimisation of a deep neural network for 3D object detection in a point cloud. We performed the experiments for the PointPillars network, which offers a reasonable compromise between detection accuracy and calculation complexity. This will allow for real-time LiDAR data processing with low energy consumption.
  arXiv  Detail & Related papers  (2020-07-01T13:50:42Z)

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.