OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs

• URL: http://arxiv.org/abs/2411.15653v1
• Date: Sat, 23 Nov 2024 21:17:35 GMT
• Title: OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs
• Authors: Chen Xin, Thomas Motz, Andreas Hartel, Enkelejda Kasneci,
• Abstract summary: OCDet is a lightweight Object Center Detection framework optimized for edge devices with NPUs. OCDet predicts heatmaps representing object center probabilities and extracts center points through peak identification. Built on NPU-friendly Semantic FPN with MobileNetV4 backbones, OCDet models are trained by our Balanced Continuous Focal Loss (BCFL)
• Score: 7.969347737723115
• License:
• Abstract: Real-time object localization on edge devices is fundamental for numerous applications, ranging from surveillance to industrial automation. Traditional frameworks, such as object detection, segmentation, and keypoint detection, struggle in resource-constrained environments, often resulting in substantial target omissions. To address these challenges, we introduce OCDet, a lightweight Object Center Detection framework optimized for edge devices with NPUs. OCDet predicts heatmaps representing object center probabilities and extracts center points through peak identification. Unlike prior methods using fixed Gaussian distribution, we introduce Generalized Centerness (GC) to generate ground truth heatmaps from bounding box annotations, providing finer spatial details without additional manual labeling. Built on NPU-friendly Semantic FPN with MobileNetV4 backbones, OCDet models are trained by our Balanced Continuous Focal Loss (BCFL), which alleviates data imbalance and focuses training on hard negative examples for probability regression tasks. Leveraging the novel Center Alignment Score (CAS) with Hungarian matching, we demonstrate that OCDet consistently outperforms YOLO11 in object center detection, achieving up to 23% higher CAS while requiring 42% fewer parameters, 34% less computation, and 64% lower NPU latency. When compared to keypoint detection frameworks, OCDet achieves substantial CAS improvements up to 186% using identical models. By integrating GC, BCFL, and CAS, OCDet establishes a new paradigm for efficient and robust object center detection on edge devices with NPUs. The code is released at https://github.com/chen-xin-94/ocdet.

Related papers

• Center Focusing Network for Real-Time LiDAR Panoptic Segmentation [58.1194137706868]
  A novel center focusing network (CFNet) is introduced to achieve accurate and real-time LiDAR panoptic segmentation. CFFE is proposed to explicitly understand the relationships between the original LiDAR points and virtual instance centers. Our CFNet outperforms all existing methods by a large margin and is 1.6 times faster than the most efficient method.
  arXiv  Detail & Related papers  (2023-11-16T01:52:11Z)
• Feature Selection using Sparse Adaptive Bottleneck Centroid-Encoder [1.2487990897680423]
  We introduce a novel nonlinear model, Sparse Adaptive Bottleneckid-Encoder (SABCE), for determining the features that discriminate between two or more classes. The algorithm is applied to various real-world data sets, including high-dimensional biological, image, speech, and accelerometer sensor data.
  arXiv  Detail & Related papers  (2023-06-07T21:37:21Z)
• Point-to-Box Network for Accurate Object Detection via Single Point Supervision [51.95993495703855]
  We introduce a lightweight alternative to the off-the-shelf proposal (OTSP) method. P2BNet can construct an inter-objects balanced proposal bag by generating proposals in an anchor-like way. The code will be released at COCO.com/ucas-vg/P2BNet.
  arXiv  Detail & Related papers  (2022-07-14T11:32:00Z)
• CenterNet++ for Object Detection [174.59360147041673]
  Bottom-up approaches are as competitive as the top-down and enjoy higher recall. Our approach, named CenterNet, detects each object as a triplet keypoints (top-left and bottom-right corners and the center keypoint) On the MS-COCO dataset, CenterNet with Res2Net-101 and Swin-Transformer achieves APs of 53.7% and 57.1%, respectively.
  arXiv  Detail & Related papers  (2022-04-18T16:45:53Z)
• DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection [16.21161769128316]
  We present DAFNe: A one-stage Anchor-Free deep Network for oriented object detection. As an anchor-free model, DAFNe reduces the prediction complexity by refraining from employing bounding box anchors. We introduce an orientation-aware generalization of the center-ness function for arbitrarily oriented bounding boxes to down-weight low-quality predictions.
  arXiv  Detail & Related papers  (2021-09-13T17:37:20Z)
• Corner Proposal Network for Anchor-free, Two-stage Object Detection [174.59360147041673]
  The goal of object detection is to determine the class and location of objects in an image. This paper proposes a novel anchor-free, two-stage framework which first extracts a number of object proposals. We demonstrate that these two stages are effective solutions for improving recall and precision.
  arXiv  Detail & Related papers  (2020-07-27T19:04:57Z)
• A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds [54.73161039445703]
  We propose a novel self-training approach that enables a typical object detector trained only with point-level annotations. During training, we utilize the available point annotations to supervise the estimation of the center points of objects. Experimental results show that our approach significantly outperforms state-of-the-art point-supervised methods under both detection and counting tasks.
  arXiv  Detail & Related papers  (2020-07-25T02:14:42Z)
• CenterNet3D: An Anchor Free Object Detector for Point Cloud [14.506796247331584]
  We propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well.
  arXiv  Detail & Related papers  (2020-07-13T13:53:56Z)
• FCOS: A simple and strong anchor-free object detector [111.87691210818194]
  We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free.
  arXiv  Detail & Related papers  (2020-06-14T01:03:39Z)
• CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection [20.86058667479973]
  In this paper, we propose CentripetalNet which uses centripetal shift to pair corner keypoints from the same instance. CentripetalNet predicts the position and the centripetal shift of the corner points and matches corners whose shifted results are aligned. On MS-COCO test-dev, our CentripetalNet not only outperforms all existing anchor-free detectors with an AP of 48.0% but also achieves comparable performance to the state-of-the-art instance segmentation approaches with a 40.2% MaskAP.
  arXiv  Detail & Related papers  (2020-03-20T06:23:32Z)

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.