Spatio-temporal Data Augmentation for Visual Surveillance
- URL: http://arxiv.org/abs/2101.09895v3
- Date: Mon, 15 Feb 2021 02:58:00 GMT
- Title: Spatio-temporal Data Augmentation for Visual Surveillance
- Authors: Jae-Yeul Kim, Jong-Eun Ha
- Abstract summary: We propose a data augmentation technique suitable for visual surveillance for additional performance improvement.
Two data augmentation methods of adjusting background model images and past images are proposed.
It is shown that performance can be improved in difficult areas such as static and ghost objects, compared to previous studies.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Visual surveillance aims to stably detect a foreground object using a
continuous image acquired from a fixed camera. Recent deep learning methods
based on supervised learning show superior performance compared to classical
background subtraction algorithms. However, there is still a room for
improvement in static foreground, dynamic background, hard shadow, illumination
changes, camouflage, etc. In addition, most of the deep learning-based methods
operates well on environments similar to training. If the testing environments
are different from training ones, their performance degrades. As a result,
additional training on those operating environments is required to ensure a
good performance. Our previous work which uses spatio-temporal input data
consisted of a number of past images, background images and current image
showed promising results in different environments from training, although it
uses a simple U-NET structure. In this paper, we propose a data augmentation
technique suitable for visual surveillance for additional performance
improvement using the same network used in our previous work. In deep learning,
most data augmentation techniques deal with spatial-level data augmentation
techniques for use in image classification and object detection. In this paper,
we propose a new method of data augmentation in the spatio-temporal dimension
suitable for our previous work. Two data augmentation methods of adjusting
background model images and past images are proposed. Through this, it is shown
that performance can be improved in difficult areas such as static foreground
and ghost objects, compared to previous studies. Through quantitative and
qualitative evaluation using SBI, LASIESTA, and our own dataset, we show that
it gives superior performance compared to deep learning-based algorithms and
background subtraction algorithms.
Related papers
- Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate.
We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data.
Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
arXiv Detail & Related papers (2024-03-23T22:32:06Z) - Deep Learning Training Procedure Augmentations [0.0]
Recent advances in Deep Learning have greatly improved performance on various tasks such as object detection, image segmentation, sentiment analysis.
While this has lead to great results, many of which with real-world applications, other relevant aspects of deep learning have remained neglected and unknown.
We will present several novel deep learning training techniques which, while capable of offering significant performance gains, also reveal several interesting analysis results regarding convergence speed, optimization landscape, and adversarial robustness.
arXiv Detail & Related papers (2022-11-25T22:31:11Z) - An Adaptive Threshold for the Canny Edge Detection with Actor-Critic
Algorithm [0.0]
In deep learning-based object detection algorithms, the detection ability is superior to classical background subtraction (BGS) algorithms.
This paper proposes a foreground-temporal fusion network (STFN) that could extract temporal and spatial information.
The proposed algorithm shows 11.28% and 18.33% higher than the latest deep learning method in the LASIESTA and SBI dataset.
arXiv Detail & Related papers (2022-09-19T01:15:32Z) - Augmentation Learning for Semi-Supervised Classification [13.519613713213277]
We propose a Semi-Supervised Learning method that automatically selects the most effective data augmentation policy for a particular dataset.
We show how policy learning can be used to adapt augmentations to datasets beyond ImageNet.
arXiv Detail & Related papers (2022-08-03T10:06:51Z) - CoDo: Contrastive Learning with Downstream Background Invariance for
Detection [10.608660802917214]
We propose a novel object-level self-supervised learning method, called Contrastive learning with Downstream background invariance (CoDo)
The pretext task is converted to focus on instance location modeling for various backgrounds, especially for downstream datasets.
Experiments on MSCOCO demonstrate that the proposed CoDo with common backbones, ResNet50-FPN, yields strong transfer learning results for object detection.
arXiv Detail & Related papers (2022-05-10T01:26:15Z) - On Efficient Transformer and Image Pre-training for Low-level Vision [74.22436001426517]
Pre-training has marked numerous state of the arts in high-level computer vision.
We present an in-depth study of image pre-training.
We find pre-training plays strikingly different roles in low-level tasks.
arXiv Detail & Related papers (2021-12-19T15:50:48Z) - Object-aware Contrastive Learning for Debiased Scene Representation [74.30741492814327]
We develop a novel object-aware contrastive learning framework that localizes objects in a self-supervised manner.
We also introduce two data augmentations based on ContraCAM, object-aware random crop and background mixup, which reduce contextual and background biases during contrastive self-supervised learning.
arXiv Detail & Related papers (2021-07-30T19:24:07Z) - Rectifying the Shortcut Learning of Background: Shared Object
Concentration for Few-Shot Image Recognition [101.59989523028264]
Few-Shot image classification aims to utilize pretrained knowledge learned from a large-scale dataset to tackle a series of downstream classification tasks.
We propose COSOC, a novel Few-Shot Learning framework, to automatically figure out foreground objects at both pretraining and evaluation stage.
arXiv Detail & Related papers (2021-07-16T07:46:41Z) - Salient Objects in Clutter [130.63976772770368]
This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets.
This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
We propose a new high-quality dataset and update the previous saliency benchmark.
arXiv Detail & Related papers (2021-05-07T03:49:26Z) - Distilling Localization for Self-Supervised Representation Learning [82.79808902674282]
Contrastive learning has revolutionized unsupervised representation learning.
Current contrastive models are ineffective at localizing the foreground object.
We propose a data-driven approach for learning in variance to backgrounds.
arXiv Detail & Related papers (2020-04-14T16:29:42Z) - Improving Learning Effectiveness For Object Detection and Classification
in Cluttered Backgrounds [6.729108277517129]
This paper develops a framework that permits to autonomously generate a training dataset in heterogeneous cluttered backgrounds.
It is clear that the learning effectiveness of the proposed framework should be improved in complex and heterogeneous environments.
The performance of the proposed framework is investigated through empirical tests and compared with that of the model trained with the COCO dataset.
arXiv Detail & Related papers (2020-02-27T22:28:48Z)
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.