AMRNet: Chips Augmentation in Aerial Images Object Detection
- URL: http://arxiv.org/abs/2009.07168v2
- Date: Sun, 25 Oct 2020 08:38:25 GMT
- Title: AMRNet: Chips Augmentation in Aerial Images Object Detection
- Authors: Zhiwei Wei, Chenzhen Duan, Xinghao Song, Ye Tian, Hongpeng Wang
- Abstract summary: Three augmentation methods are introduced to relieve problems such as scale variation, object sparsity, and class imbalance.
Our model achieves state-of-the-art perfomance on two popular aerial image datasets of VisDrone and UAVDT.
- Score: 7.817259518365044
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Object detection in aerial images is a challenging task due to the following
reasons: (1) objects are small and dense relative to images; (2) the object
scale varies in a wide range; (3) the number of object in different classes is
imbalanced. Many current methods adopt cropping idea: splitting high resolution
images into serials subregions (chips) and detecting on them. However, some
problems such as scale variation, object sparsity, and class imbalance exist in
the process of training network with chips. In this work, three augmentation
methods are introduced to relieve these problems. Specifically, we propose a
scale adaptive module, which dynamically adjusts chip size to balance object
scale, narrowing scale variation in training. In addtion, we introduce mosaic
to augment datasets, relieving object sparity problem. To balance catgory, we
present mask resampling to paste object in chips with panoramic segmentation.
Our model achieves state-of-the-art perfomance on two popular aerial image
datasets of VisDrone and UAVDT. Remarkably, three methods can be independently
applied to detectiors, increasing performance steady without the sacrifice of
inference efficiency.
Related papers
- Iterative Object Count Optimization for Text-to-image Diffusion Models [59.03672816121209]
Current models, which learn from image-text pairs, inherently struggle with counting.
We propose optimizing the generated image based on a counting loss derived from a counting model that aggregates an object's potential.
We evaluate the generation of various objects and show significant improvements in accuracy.
arXiv Detail & Related papers (2024-08-21T15:51:46Z) - DASSF: Dynamic-Attention Scale-Sequence Fusion for Aerial Object Detection [6.635903943457569]
The original YOLO algorithm has low overall detection accuracy due to its weak ability to perceive targets of different scales.
This paper proposes a dynamic-attention scale-sequence fusion algorithm (DASSF) for small target detection in aerial images.
Experimental results show that when the DASSF method is applied to YOLOv8, compared to YOLOv8n, the model shows an increase of 9.2% and 2.4% in the mean average precision (mAP)
arXiv Detail & Related papers (2024-06-18T05:26:44Z) - YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images [33.80392696735718]
YOLC (You Only Look Clusters) is an efficient and effective framework that builds on an anchor-free object detector, CenterNet.
To overcome the challenges posed by large-scale images and non-uniform object distribution, we introduce a Local Scale Module (LSM) that adaptively searches cluster regions for zooming in for accurate detection.
We perform extensive experiments on two aerial image datasets, including Visdrone 2019 and UAVDT, to demonstrate the effectiveness and superiority of our proposed approach.
arXiv Detail & Related papers (2024-04-09T10:03:44Z) - Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery [51.73680703579997]
We present a neural radiance field method for urban-scale semantic and building-level instance segmentation from aerial images.
objects in urban aerial images exhibit substantial variations in size, including buildings, cars, and roads.
We introduce a scale-adaptive semantic label fusion strategy that enhances the segmentation of objects of varying sizes.
We then introduce a novel cross-view instance label grouping strategy to mitigate the multi-view inconsistency problem in the 2D instance labels.
arXiv Detail & Related papers (2024-03-18T14:15:39Z) - ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object
Detection [24.085715205081385]
We denote size of an object as the number of pixels it covers in an image and size imbalance as the over-representation of certain sizes of objects in a dataset.
We propose a novel ARchitectUre-agnostic BAlanced Loss (ARUBA) that can be applied as a plugin on top of any object detection model.
arXiv Detail & Related papers (2022-10-10T11:28:16Z) - Scale Normalized Image Pyramids with AutoFocus for Object Detection [75.71320993452372]
A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a fixed size range at different scales.
We propose an efficient spatial sub-sampling scheme which only operates on fixed-size sub-regions likely to contain objects.
The resulting algorithm is referred to as AutoFocus and results in a 2.5-5 times speed-up during inference when used with SNIP.
arXiv Detail & Related papers (2021-02-10T18:57:53Z) - Bidirectional Multi-scale Attention Networks for Semantic Segmentation
of Oblique UAV Imagery [30.524771772192757]
We propose the novel bidirectional multi-scale attention networks, which fuse features from multiple scales bidirectionally for more adaptive and effective feature extraction.
Our model achieved the state-of-the-art (SOTA) result with a mean intersection over union (mIoU) score of 70.80%.
arXiv Detail & Related papers (2021-02-05T11:02:15Z) - Counting from Sky: A Large-scale Dataset for Remote Sensing Object
Counting and A Benchmark Method [52.182698295053264]
We are interested in counting dense objects from remote sensing images. Compared with object counting in a natural scene, this task is challenging in the following factors: large scale variation, complex cluttered background, and orientation arbitrariness.
To address these issues, we first construct a large-scale object counting dataset with remote sensing images, which contains four important geographic objects.
We then benchmark the dataset by designing a novel neural network that can generate a density map of an input image.
arXiv Detail & Related papers (2020-08-28T03:47:49Z) - Multi-scale Interactive Network for Salient Object Detection [91.43066633305662]
We propose the aggregate interaction modules to integrate the features from adjacent levels.
To obtain more efficient multi-scale features, the self-interaction modules are embedded in each decoder unit.
Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches.
arXiv Detail & Related papers (2020-07-17T15:41:37Z) - Counting dense objects in remote sensing images [52.182698295053264]
Estimating number of interested objects from a given image is a challenging yet important task.
In this paper, we are interested in counting dense objects from remote sensing images.
To address these issues, we first construct a large-scale object counting dataset based on remote sensing images.
We then benchmark the dataset by designing a novel neural network which can generate density map of an input image.
arXiv Detail & Related papers (2020-02-14T09:13:54Z)
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.