Plug & Play Convolutional Regression Tracker for Video Object Detection
- URL: http://arxiv.org/abs/2003.00981v1
- Date: Mon, 2 Mar 2020 15:57:55 GMT
- Title: Plug & Play Convolutional Regression Tracker for Video Object Detection
- Authors: Ye Lyu, Michael Ying Yang, George Vosselman, Gui-Song Xia
- Abstract summary: 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.
- Score: 37.47222104272429
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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. As the appearance of objects may deteriorate in some frames, features or
detections from the other frames are commonly used to enhance the prediction.
In this paper, we propose a Plug & Play scale-adaptive convolutional regression
tracker for the video object detection task, which could be easily and
compatibly implanted into the current state-of-the-art detection networks. As
the tracker reuses the features from the detector, it is a very light-weighted
increment to the detection network. The whole network performs at the speed
close to a standard object detector. With our new video object detection
pipeline design, image object detectors can be easily turned into efficient
video object detectors without modifying any parameters. The performance is
evaluated on the large-scale ImageNet VID dataset. Our Plug & Play design
improves mAP score for the image detector by around 5% with only little speed
drop.
Related papers
- FADE: A Dataset for Detecting Falling Objects around Buildings in Video [75.48118923174712]
Falling objects from buildings can cause severe injuries to pedestrians due to the great impact force they exert.
FADE contains 1,881 videos from 18 scenes, featuring 8 falling object categories, 4 weather conditions, and 4 video resolutions.
We develop a new object detection method called FADE-Net, which effectively leverages motion information.
arXiv Detail & Related papers (2024-08-11T11:43:56Z) - FOLT: Fast Multiple Object Tracking from UAV-captured Videos Based on
Optical Flow [27.621524657473945]
Multiple object tracking (MOT) has been successfully investigated in computer vision.
However, MOT for the videos captured by unmanned aerial vehicles (UAV) is still challenging due to small object size, blurred object appearance, and very large and/or irregular motion.
We propose FOLT to mitigate these problems and reach fast and accurate MOT in UAV view.
arXiv Detail & Related papers (2023-08-14T15:24:44Z) - Memory Maps for Video Object Detection and Tracking on UAVs [14.573513188682183]
This paper introduces a novel approach to video object detection and tracking on Unmanned Aerial Vehicles (UAVs)
By incorporating metadata, the proposed approach creates a memory map of object locations in actual world coordinates.
We use this representation to boost confidences, resulting in improved performance for several temporal computer vision tasks.
arXiv Detail & Related papers (2023-03-06T21:29:45Z) - Implicit Motion Handling for Video Camouflaged Object Detection [60.98467179649398]
We propose a new video camouflaged object detection (VCOD) framework.
It can exploit both short-term and long-term temporal consistency to detect camouflaged objects from video frames.
arXiv Detail & Related papers (2022-03-14T17:55:41Z) - Recent Trends in 2D Object Detection and Applications in Video Event
Recognition [0.76146285961466]
We discuss the pioneering works in object detection, followed by the recent breakthroughs that employ deep learning.
We highlight recent datasets for 2D object detection both in images and videos, and present a comparative performance summary of various state-of-the-art object detection techniques.
arXiv Detail & Related papers (2022-02-07T14:15:11Z) - Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K
Videos using a Joint Detection-and-Tracking Approach [19.59528430884104]
We present a neural network model called the Recurrent Correlational Network, where detection and tracking are jointly performed.
In experiments with datasets containing images of scenes with small flying objects, such as birds and unmanned aerial vehicles, the proposed method yielded consistent improvements.
Our network performs as well as state-of-the-art generic object trackers when it was evaluated as a tracker on a bird image dataset.
arXiv Detail & Related papers (2021-05-18T03:22:03Z) - Few-Shot Learning for Video Object Detection in a Transfer-Learning
Scheme [70.45901040613015]
We study the new problem of few-shot learning for video object detection.
We employ a transfer-learning framework to effectively train the video object detector on a large number of base-class objects and a few video clips of novel-class objects.
arXiv Detail & Related papers (2021-03-26T20:37:55Z) - Ensembling object detectors for image and video data analysis [98.26061123111647]
We propose a method for ensembling the outputs of multiple object detectors for improving detection performance and precision of bounding boxes on image data.
We extend it to video data by proposing a two-stage tracking-based scheme for detection refinement.
arXiv Detail & Related papers (2021-02-09T12:38:16Z) - 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) - Joint Detection and Tracking in Videos with Identification Features [36.55599286568541]
We propose the first joint optimization of detection, tracking and re-identification features for videos.
Our method reaches the state-of-the-art on MOT, it ranks 1st in the UA-DETRAC'18 tracking challenge among online trackers, and 3rd overall.
arXiv Detail & Related papers (2020-05-21T21:06:40Z)
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.