Object Detection Binary Classifiers methodology based on deep learning to identify small objects handled similarly: Application in video surveillance

Pérez-Hernández, Francisco; Tabik, Siham; Lamas, A.; Olmos, Roberto; Fujita, Hamido; Herrera, Francisco

doi:10.1016/j.knosys.2020.105590

Cited by 134 publications

(63 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The general flow diagram of the proposed study is given in Figure 2. In this study, a data set suitable for the purposes was created by collecting images from open access data sets [9,[12][13][14], which have repeatedly been the source of many previous studies in the literature and original internet browsers and video pages [4,15]. This dataset has 16000 images containing 9500 knives, 3500 guns, and 3000 ordinary pictures.…”

Section: Materıal and Methodsmentioning

confidence: 99%

Deep Neural Networks Based on Transfer Learning Approaches to Classification of Gun and Knife Images

AĞDAŞ¹,

Türkoğlu²,

Gülseçen³

2021

Sakarya University Journal of Computer and Information Sciences

View full text Add to dashboard Cite

Most of the criminal acts are performed using criminal tools. One of the most effective ways of preventing crime is to observe and detect offensive weapons by security camera systems. Deep learning techniques can show very high-performance in observing and perceiving objects. In the current study, the performances of the pre-trained AlexNet, VGG16, and VGG19 models based on convolutional neural networks, were tested for the detection and classification of criminal tools such as guns and knives. In the study, the training process was carried out using transfer learning approaches such as Fine-tuning and Training from scratch based on deep architectures. To test the deep architectures used in the proposed study, the gun and knife datasets frequently used in the literature were collected and combined with new datasets obtained originally from search engines and videos, and then their performances were tested. In the experimental results, the VGG16 model based on fine-tuning for the two and three classes achieved the highest accuracy in detecting criminal devices with a rate of 99.73% and 99.67%, respectively. As a result, the study has observed that offensive weapons could be detected with security cameras using learned weights of deep architectures.

show abstract

Section: Materıal and Methodsmentioning

confidence: 99%

Deep Neural Networks Based on Transfer Learning Approaches to Classification of Gun and Knife Images

AĞDAŞ¹,

Türkoğlu²,

Gülseçen³

2021

Sakarya University Journal of Computer and Information Sciences

View full text Add to dashboard Cite

show abstract

“…Taherkhani et al [30] propose a transfer learning based multiclass imbalanced classification method by combining an adaptive boosting algorithm and neural networks. Pérez-Hernández et al [31] describe binarization techniques on neural networks, which convert a multi-class task into several binary tasks to reduce multi-class imbalance problems. In recent years, some interesting imbalanced dataset processing methods specifically for deep learning have been developed.…”

Section: Related Workmentioning

confidence: 99%

BBW: a batch balance wrapper for training deep neural networks on extremely imbalanced datasets with few minority samples

Zhang

Liu

et al. 2021

Appl Intell

View full text Add to dashboard Cite

In recent years, Deep Neural Networks (DNNs) have achieved excellent performance on many tasks, but it is very difficult to train good models from imbalanced datasets. Creating balanced batches either by majority data down-sampling or by minority data up-sampling can solve the problem in certain cases. However, it may lead to learning process instability and overfitting. In this paper, we propose the Batch Balance Wrapper (BBW), a novel framework which can adapt a general DNN to be well trained from extremely imbalanced datasets with few minority samples. In BBW, two extra network layers are added to the start of a DNN. The layers prevent overfitting of minority samples and improve the expressiveness of the sample distribution of minority samples. Furthermore, Batch Balance (BB), a class-based sampling algorithm, is proposed to make sure the samples in each batch are always balanced during the learning process. We test BBW on three well-known extremely imbalanced datasets with few minority samples. The maximum imbalance ratio reaches 1167:1 with only 16 positive samples. Compared with existing approaches, BBW achieves better classification performance. In addition, BBW-wrapped DNNs are 16.39 times faster, relative to unwrapped DNNs. Moreover, BBW does not require data preprocessing or additional hyper-parameter tuning, operations that may require additional processing time. The experiments prove that BBW can be applied to common applications of extremely imbalanced data with few minority samples, such as the classification of EEG signals, medical images and so on.

show abstract

“…In recent years, Deep Learning (DL) approaches have been proposed to replace handcrafted techniques in computer vision applications. They showed impressive results in various tasks such as autonomous vehicles [3], pedestrian detection [4], and video surveillance [5,6]. DL approaches are used in forest fire segmentation tasks to extract the geometrical characteristics of the fire, such as height, width, angle, and so forth.…”

Section: Introductionmentioning

confidence: 99%

Wildfire Segmentation Using Deep Vision Transformers

Ghali

Akhloufi

Jmal³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

In this paper, we address the problem of forest fires’ early detection and segmentation in order to predict their spread and help with fire fighting. Techniques based on Convolutional Networks are the most used and have proven to be efficient at solving such a problem. However, they remain limited in modeling the long-range relationship between objects in the image, due to the intrinsic locality of convolution operators. In order to overcome this drawback, Transformers, designed for sequence-to-sequence prediction, have emerged as alternative architectures. They have recently been used to determine the global dependencies between input and output sequences using the self-attention mechanism. In this context, we present in this work the very first study, which explores the potential of vision Transformers in the context of forest fire segmentation. Two vision-based Transformers are used, TransUNet and MedT. Thus, we design two frameworks based on the former image Transformers adapted to our complex, non-structured environment, which we evaluate using varying backbones and we optimize for forest fires’ segmentation. Extensive evaluations of both frameworks revealed a performance superior to current methods. The proposed approaches achieved a state-of-the-art performance with an F1-score of 97.7% for TransUNet architecture and 96.0% for MedT architecture. The analysis of the results showed that these models reduce fire pixels mis-classifications thanks to the extraction of both global and local features, which provide finer detection of the fire’s shape.

show abstract

Object Detection Binary Classifiers methodology based on deep learning to identify small objects handled similarly: Application in video surveillance

Cited by 134 publications

References 20 publications

Deep Neural Networks Based on Transfer Learning Approaches to Classification of Gun and Knife Images

Deep Neural Networks Based on Transfer Learning Approaches to Classification of Gun and Knife Images

BBW: a batch balance wrapper for training deep neural networks on extremely imbalanced datasets with few minority samples

Wildfire Segmentation Using Deep Vision Transformers

Contact Info

Product

Resources

About