Pack and Detect: Fast Object Detection in Videos Using Region-of-Interest Packing

• URL: http://arxiv.org/abs/1809.01701v5
• Date: Wed, 17 Jul 2024 02:09:10 GMT
• Title: Pack and Detect: Fast Object Detection in Videos Using Region-of-Interest Packing
• Authors: Athindran Ramesh Kumar, Balaraman Ravindran, Anand Raghunathan,
• Abstract summary: We propose Pack and Detect, an approach to reduce the computational requirements of object detection in videos. Experiments using the ImageNet video object detection dataset indicate that PaD can potentially reduce the number of FLOPS required for a frame by $4times$.
• Score: 15.162117090697006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object detection in videos is an important task in computer vision for various applications such as object tracking, video summarization and video search. Although great progress has been made in improving the accuracy of object detection in recent years due to the rise of deep neural networks, the state-of-the-art algorithms are highly computationally intensive. In order to address this challenge, we make two important observations in the context of videos: (i) Objects often occupy only a small fraction of the area in each video frame, and (ii) There is a high likelihood of strong temporal correlation between consecutive frames. Based on these observations, we propose Pack and Detect (PaD), an approach to reduce the computational requirements of object detection in videos. In PaD, only selected video frames called anchor frames are processed at full size. In the frames that lie between anchor frames (inter-anchor frames), regions of interest (ROIs) are identified based on the detections in the previous frame. We propose an algorithm to pack the ROIs of each inter-anchor frame together into a reduced-size frame. The computational requirements of the detector are reduced due to the lower size of the input. In order to maintain the accuracy of object detection, the proposed algorithm expands the ROIs greedily to provide additional background around each object to the detector. PaD can use any underlying neural network architecture to process the full-size and reduced-size frames. Experiments using the ImageNet video object detection dataset indicate that PaD can potentially reduce the number of FLOPS required for a frame by $4\times$. This leads to an overall increase in throughput of $1.25\times$ on a 2.1 GHz Intel Xeon server with a NVIDIA Titan X GPU at the cost of $1.1\%$ drop in accuracy.

Related papers

• Practical Video Object Detection via Feature Selection and Aggregation [18.15061460125668]
  Video object detection (VOD) needs to concern the high across-frame variation in object appearance, and the diverse deterioration in some frames. Most of contemporary aggregation methods are tailored for two-stage detectors, suffering from high computational costs. This study invents a very simple yet potent strategy of feature selection and aggregation, gaining significant accuracy at marginal computational expense.
  arXiv  Detail & Related papers  (2024-07-29T02:12:11Z)
• 3D Small Object Detection with Dynamic Spatial Pruning [62.72638845817799]
  We propose an efficient feature pruning strategy for 3D small object detection. We present a multi-level 3D detector named DSPDet3D which benefits from high spatial resolution. It takes less than 2s to directly process a whole building consisting of more than 4500k points while detecting out almost all objects.
  arXiv  Detail & Related papers  (2023-05-05T17:57:04Z)
• FrameHopper: Selective Processing of Video Frames in Detection-driven Real-Time Video Analytics [2.5119455331413376]
  Detection-driven real-time video analytics require continuous detection of objects contained in the video frames. Running these detectors on each and every frame in resource-constrained edge devices is computationally intensive. We propose an off-line Reinforcement Learning (RL)-based algorithm to determine these skip-lengths.
  arXiv  Detail & Related papers  (2022-03-22T07:05:57Z)
• Video Salient Object Detection via Contrastive Features and Attention Modules [106.33219760012048]
  We propose a network with attention modules to learn contrastive features for video salient object detection. A co-attention formulation is utilized to combine the low-level and high-level features. We show that the proposed method requires less computation, and performs favorably against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-11-03T17:40:32Z)
• rSVDdpd: A Robust Scalable Video Surveillance Background Modelling Algorithm [13.535770763481905]
  We present a new video surveillance background modelling algorithm based on a new robust singular value decomposition technique rSVDdpd. We also demonstrate the superiority of our proposed algorithm on a benchmark dataset and a new real-life video surveillance dataset in the presence of camera tampering.
  arXiv  Detail & Related papers  (2021-09-22T12:20:44Z)
• FOVEA: Foveated Image Magnification for Autonomous Navigation [53.69803081925454]
  We propose an attentional approach that elastically magnifies certain regions while maintaining a small input canvas. Our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning. On the autonomous driving datasets Argoverse-HD and BDD100K, we show our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning.
  arXiv  Detail & Related papers  (2021-08-27T03:07:55Z)
• You Better Look Twice: a new perspective for designing accurate detectors with reduced computations [56.34005280792013]
  BLT-net is a new low-computation two-stage object detection architecture. It reduces computations by separating objects from background using a very lite first-stage. Resulting image proposals are then processed in the second-stage by a highly accurate model.
  arXiv  Detail & Related papers  (2021-07-21T12:39:51Z)
• Single Shot Video Object Detector [215.06904478667337]
  Single Shot Video Object Detector (SSVD) is a new architecture that novelly integrates feature aggregation into a one-stage detector for object detection in videos. For $448 times 448$ input, SSVD achieves 79.2% mAP on ImageNet VID dataset.
  arXiv  Detail & Related papers  (2020-07-07T15:36:26Z)
• RN-VID: A Feature Fusion Architecture for Video Object Detection [10.667492516216889]
  We propose RN-VID (standing for RetinaNet-VIDeo), a novel approach to video object detection. First, we propose a new architecture that allows the usage of information from nearby frames to enhance feature maps. Second, we propose a novel module to merge feature maps of same dimensions using re-ordering of channels and 1 x 1 convolutions.
  arXiv  Detail & Related papers  (2020-03-24T14:54:46Z)
• Plug & Play Convolutional Regression Tracker for Video Object Detection [37.47222104272429]
  Video object detection targets to simultaneously localize the bounding boxes of the objects and identify their classes in a given video. One challenge for video object detection is to consistently detect all objects across the whole video. We propose a Plug & Play scale-adaptive convolutional regression tracker for the video object detection task.
  arXiv  Detail & Related papers  (2020-03-02T15:57:55Z)
• ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection [69.68263074432224]
  We present a novel framework named ZoomNet for stereo imagery-based 3D detection. The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes. To further exploit the abundant texture cues in RGB images for more accurate disparity estimation, we introduce a conceptually straight-forward module -- adaptive zooming.
  arXiv  Detail & Related papers  (2020-03-01T17:18:08Z)

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.