Search

Image restoration under adverse weather conditions poses a challenging task. Previous research efforts have predominantly focused on eliminating rain and fog phenomena from images. However, snow, being another common atmospheric occurrence, also significantly impacts advanced computer vision tasks such as object detection and semantic segmentation. Recently, there has been a surge of methods specifically targeting snow removal, with the majority employing visual Transformers as the backbone network to enhance restoration effectiveness. Nevertheless, due to the quadratic computations required by Transformers to model long-range dependencies, this significantly escalates the time and space consumption of deep learning models. To address this issue, this paper proposes an efficient snow removal Transformer with a global windowing network (SGNet). This method forgoes the localized windowing strategy of previous visual Transformers, opting instead to partition the image into multiple low-resolution subimages containing global information using wavelet sampling, thereby ensuring higher performance while reducing computational overhead. Extensive experimentation demonstrates that our approach achieves outstanding performance across a wide range of benchmark datasets and can rival methods employing CNNs in terms of computational cost. [ABSTRACT FROM AUTHOR]

Image deblurring attracts research attention in the field of image processing and computer vision. Traditional deblurring methods based on statistical prior largely depend on the selected prior type, which limits their restoring ability. Moreover, the constructed deblurring model is difficult to solve, and the operation is comparatively complicated. Meanwhile, deep learning has become a hotspot in various fields in recent years. End-to-end convolutional neural networks (CNNs) can learn the pixel mapping relationships between degraded images and clear images. In addition, they can also obtain the result of effectively eliminating spatial variable blurring. However, conventional CNNs have some disadvantages in generalization ability and details of the restored image. Therefore, this paper presents an iterative dual CNN called IDC for image deblurring, where the task of image deblurring is divided into two sub-networks: deblurring and detail restoration. The deblurring sub-network adopts a U-Net structure to learn the semantical and structural features of the image, and the detail restoration sub-network utilizes a shallow and wide structure without downsampling, where only the image texture features are extracted. Finally, to obtain the deblurred image, this paper presents a multiscale iterative strategy that effectively improves the robustness and precision of the model. The experimental results showed that the proposed method has an excellent effect of deblurring on a real blurred image dataset and is suitable for various real application scenes. [ABSTRACT FROM AUTHOR]

Person re-identification has become an essential application within computer vision due to its ability to match the same person over non-overlapping cameras. However, it is a challenging task because of the broad view of cameras with a large number of pedestrians appearing with various poses. As a result, various approaches of supervised model learning have been utilized to locate and identify a person based on the given input. Nevertheless, several of these approaches perform worse than expected in retrieving the right person in real-time over multiple CCTVs/camera views. This is due to inaccurate segmentation of the person, leading to incorrect classification. This paper proposes an efficient and real-time person re-identification system, named ReID-DeePNet system. It is based on fusing the matching scores generated by two different deep learning models, convolutional neural network and deep belief network, to extract discriminative feature representations from the pedestrian image. Initially, a segmentation procedure was developed based on merging the advantages of the Mask R-CNN and GrabCut algorithm to tackle the adverse effects caused by background clutter. Afterward, the two different deep learning models extracted discriminative feature representations from the pedestrian segmented image, and their matching scores were fused to make the final decision. Several extensive experiments were conducted, using three large-scale and challenging person re-identification datasets: Market-1501, CUHK03, and P-DESTRE. The ReID-DeePNet system achieved new state-of-the-art Rank-1 and mAP values on these three challenging ReID datasets. [ABSTRACT FROM AUTHOR]

Modern aviation security systems are largely tied to the work of screening operators. Due to physical characteristics, they are prone to problems such as fatigue, loss of attention, etc. There are methods for recognizing such objects, but they face such difficulties as the specific structure of luggage X-ray images. Furthermore, such systems require significant computational resources when increasing the size of models. Overcoming the first and second disadvantage can largely lie in the hardware plane. It needs new introscopes and registration techniques, as well as more powerful computing devices. However, for processing, it is more preferable to improve quality without increasing the computational power requirements of the recognition system. This can be achieved on traditional neural network architectures, but with the more complex training process. A new training approach is proposed in this study. New ways of baggage X-ray image augmentation and advanced approaches to training convolutional neural networks and vision transformer networks are proposed. It is shown that the use of ArcFace loss function for the task of the items binary classification into forbidden and allowed classes provides a gain of about 3–5% for different architectures. At the same time, the use of softmax activation function with temperature allows one to obtain more flexible estimates of the probability of belonging, which, when the threshold is set, allows one to significantly increase the accuracy of recognition of forbidden items, and when it is reduced, provides high recall of recognition. The developed augmentations based on doubly stochastic image models allow one to increase the recall of recognizing dangerous items by 1–2%. On the basis of the developed classifier, the YOLO detector was modified and the mAP gain of 0.72% was obtained. Thus, the research results are matched to the goal of increasing efficiency in X-ray baggage image processing. [ABSTRACT FROM AUTHOR]

Fire accidents occur in every part of the world and cause a large number of casualties because of the risks involved in manually extinguishing the fire. In most cases, humans cannot detect and extinguish fire manually. Fire extinguishing robots with sophisticated functionalities are being rapidly developed nowadays, and most of these systems use fire sensors and detectors. However, they lack mechanisms for the early detection of fire, in case of casualties. To detect and prevent such fire accidents in its early stages, a deep learning-based automatic fire extinguishing mechanism was introduced in this work. Fire detection and human presence in fire locations were carried out using convolution neural networks (CNNs), configured to operate on the chosen fire dataset. For fire detection, a custom learning network was formed by tweaking the layer parameters of CNN for detecting fires with better accuracy. For human detection, Alex-net architecture was employed to detect the presence of humans in the fire accident zone. We experimented and analyzed the proposed model using various optimizers, activation functions, and learning rates, based on the accuracy and loss metrics generated for the chosen fire dataset. The best combination of neural network parameters was evaluated from the model configured with an Adam optimizer and softmax activation, driven with a learning rate of 0.001, providing better accuracy for the learning model. Finally, the experiments were tested using a mobile robotic system by configuring them in automatic and wireless control modes. In automatic mode, the robot was made to patrol around and monitor for fire casualties and fire accidents. It automatically extinguished the fire using the learned features triggered through the developed model. [ABSTRACT FROM AUTHOR]

For decades, a vital area of computer vision research has been multiview stereo (MVS), which creates 3D models of a scene using photographs. This study presents an effective MVS network for 3D reconstruction utilizing multiview pictures. Alternative learning-based reconstruction techniques work well, because CNNs (convolutional neural network) can extract only the image's local features; however, they contain many artifacts. Herein, a transformer and CNN are used to extract the global and local features of the image, respectively. Additionally, hierarchical aggregation and heterogeneous interaction modules were used to improve these features. They are based on the transformer and can extract dense features with 3D consistency and global context that are necessary to provide accurate matching for MVS. [ABSTRACT FROM AUTHOR]

Surveillance systems regularly create massive video data in the modern technological era, making their analysis challenging for security specialists. Finding anomalous activities manually in these enormous video recordings is a tedious task, as they infrequently occur in the real world. We proposed a minimal complex deep learning-based model named EADN for anomaly detection that can operate in a surveillance system. At the model's input, the video is segmented into salient shots using a shot boundary detection algorithm. Next, the selected sequence of frames is given to a Convolutional Neural Network (CNN) that consists of time-distributed 2D layers for extracting salient spatiotemporal features. The extracted features are enriched with valuable information that is very helpful in capturing abnormal events. Lastly, Long Short-Term Memory (LSTM) cells are employed to learn spatiotemporal features from a sequence of frames per sample of each abnormal event for anomaly detection. Comprehensive experiments are performed on benchmark datasets. Additionally, the quantitative results are compared with state-of-the-art methods, and a substantial improvement is achieved, showing our model's effectiveness. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNNs) are very popular in many fields including computer vision, speech recognition, natural language processing, etc. Though deep learning leads to groundbreaking performance in those domains, the networks used are very computationally demanding and are far from being able to perform in real-time applications even on a GPU, which is not power efficient and therefore does not suit low power systems such as mobile devices. To overcome this challenge, some solutions have been proposed for quantizing the weights and activations of these networks, which accelerate the runtime significantly. Yet, this acceleration comes at the cost of a larger error unless spatial adjustments are carried out. The method proposed in this work trains quantized neural networks by noise injection and a learned clamping, which improve accuracy. This leads to state-of-the-art results on various regression and classification tasks, e.g., ImageNet classification with architectures such as ResNet-18/34/50 with as low as 3 bit weights and activations. We implement the proposed solution on an FPGA to demonstrate its applicability for low-power real-time applications. The quantization code will become publicly available upon acceptance. [ABSTRACT FROM AUTHOR]

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results. [ABSTRACT FROM AUTHOR]

As one of the important techniques for protecting the copyrights of digital images, content-based image copy detection has attracted a lot of attention in the past few decades. The traditional content-based copy detection methods usually extract local hand-crafted features and then quantize these features to visual words by the bag-of-visual-words (BOW) model to build an inverted index file for rapid image matching. Recently, deep learning features, such as the features derived from convolutional neural networks (CNN), have been proven to outperform the hand-crafted features in many applications of computer vision. However, it is not feasible to directly apply the existing global CNN features for copy detection, since they are usually sensitive to partial content-discarded attacks, such as copping and occlusion. Thus, we propose a local CNN feature-based image copy detection method with contextual hash embedding. We first extract the local CNN features from images and then quantize them to visual words to construct an index file. Then, as the BOW quantization process decreases the discriminability of these features to some extent, a contextual hash sequence is captured from a relatively large region surrounding each CNN feature and then is embedded into the index file to improve the feature's discriminability. Extensive experimental results demonstrate that the proposed method achieves a superior performance compared to the related works in the copy detection task. [ABSTRACT FROM AUTHOR]