Deep Residual Multi-resolution Features and Optimized Kernel ELM for Forest Fire Image Detection Using Imbalanced Database

Basketball shooting angle calculation and analysis by deeply-learned vision model

Traffic sign recognition plays an important role in autonomous vehicles as well as advanced driver assistance systems. Although various methods have been developed, it is still difficult for the state-of-the-art algorithms to obtain high recognition precision with low computational costs. In this paper, based on the investigation on the influence that color spaces have on the representation learning of convolutional neural network, a novel traffic sign recognition approach called DP-KELM is proposed by using a kernel-based extreme learning machine (KELM) classifier with deep perceptual features. Unlike the previous approaches, the representation learning process in DP-KELM is implemented in the perceptual Lab color space. Based on the learned deep perceptual feature, a kernel-based ELM classifier is trained with high computational efficiency and generalization performance. Through the experiments on the German traffic sign recognition benchmark, the proposed method is demonstrated to have higher precision than most of the state-of-the-art approaches. In particular, when compared with the hinge loss stochastic gradient descent method which has the highest precision, the proposed method can achieve a comparable recognition rate with significantly fewer computational costs.

Automated accurate fire detection system using ensemble pretrained residual network

In this paper, we propose a saliency detection model for RGB-D images based on the deep features of RGB images and depth images within a Bayesian framework. By analysing 3D saliency in the case of RGB images and depth images, the class-conditional mutual information is computed for measuring the dependence of deep features extracted using a convolutional neural network; then, the posterior probability of the RGB-D saliency is formulated by applying Bayes’ theorem. By assuming that deep features are Gaussian distributions, a discriminative mixed-membership naive Bayes (DMNB) model is used to calculate the final saliency map. The Gaussian distribution parameters can be estimated in the DMNB model by using a variational inference-based expectation maximization algorithm. The experimental results on RGB-D images from the NLPR dataset and NJU-DS400 dataset show that the proposed model performs better than other existing models.

Diseases of the digestive tract, such as ulcers, pose a serious threat to human health. In fact, many types of endoscopy are employed to examine the patient’s gastrointestinal tract. Recently, wireless capsule endoscopy (WCE) is presented as an excellent diagnostic tool for evaluation of gastrointestinal diseases compared to traditional endoscopies. This diagnosis usually takes a long time, which is tiring, and so the doctors may miss parts where abnormalities of the gastrointestinal tract may present. Therefore, automated diagnostic technics to detect symptoms of gastrointestinal illness in WCE images is adopted as an excellent enhancement tool for these doctors. In this work, a new computer-aided diagnosis method for ulcer detection in WCE images is proposed. After a preprocessing step, fine-tuned convolutional neural network (CNN) is used to extract deep features from these images. Since the number of ulcer images in the available data sets is limited, the CNN networks used in this work were pre-trained on millions of labeled natural images (ImageNet). After the deep features extraction, a random forest classifier is employed to detect ulcer from WCE images. The proposed approach demonstrates promising results (96.73 % and 95.34 % in terms of precision and recall respectively). Those results are satisfactory when compared to recent state-of-the-art methods.

Framework for psoriasis/molluscum detection in skin images using ResNetV2 variants

Chapter 14 - U-WOA: an unsupervised whale optimization algorithm based deep feature selection method for cancer detection in breast ultrasound images

An efficient dark spot detection method for offshore oil spill in SAR images based on edge-enhanced attention fusion.

The joint classification of hyperspectral image (HSI) and light detection and ranging (LiDAR) data has attracted considerable attention in the field of remote sensing. Integrating the advantages of the two data sources can provide precise data support and analytical decision-making for remote-sensing applications. However, due to the inherent differences in properties and semantic information from heterogeneous data, most existing deep-learning methods suboptimally extract the characteristic features of both data sources while utilizing their interactive information. In this letter, we propose a dual-branch feature fusion network-based cross-modal enhanced CNN and Transformer (DF2NCECT) to make full use of the respective features and interactive information of multisource data. DF2NCECT consists of two main stages. One is the basic feature extraction stage, which builds a hybrid convolution module based on 3DCNN and inception structure to fully extract the joint features of HSI from multiple spatial perspectives. The other is the deep feature fusion stage, where the CNN and Transformer are designed in parallel to fully explore and fuse deep features between HSI and LiDAR. More importantly, to achieve efficacious interactive information between HSI and LiDAR, a cross-modal enhanced CNN and Transformer module (CECT) is designed to deeply enhance the fused interactive features from global/local perspectives. Experiments show that the proposed method is superior and outperforms the comparison methods by an average of 3.06% in OA on Houston2013 and 1.79% on Summer, respectively.

The existing YOLOv5‐based framework has achieved great success in the field of target detection. However, in forest fire detection tasks, there are few high‐quality forest fire images available, and the performance of the YOLO model has suffered a serious decline in detecting small‐scale forest fires. Making full use of context information can effectively improve the performance of small target detection. To this end, this paper proposes a new graph‐embedded YOLOv5 forest fire detection framework, which can improve the performance of small‐scale forest fire detection using different scales of context information. To mine local context information, we design a spatial graph convolution operation based on the message passing neural network (MPNN) mechanism. To utilize global context information, we introduce a multi‐head self‐attention (MSA) module before each YOLO head. The experimental results on FLAME and our self‐built fire dataset show that our proposed model improves the accuracy of small‐scale forest fire detection. The proposed model achieves high performance in real‐time performance by fully utilizing the advantages of the YOLOv5 framework.

Forest fires represent one of the most severe environmental disasters, causing extensive ecological, social, and economic damage—particularly in tropical nations like Indonesia. This research introduces a hybrid framework that combines Blockchain and Neural Network technologies to classify forest fire images. The goal is not only to enhance detection precision but also to guarantee the integrity and security of experimental data. Two deep learning architectures, ResNet-50 and VGG-16, were implemented and evaluated to compare their effectiveness in differentiating fire from non-fire imagery. The dataset merges locally collected images from the Puncak area of Bogor, Indonesia, with the public FIRE dataset from Kaggle, thereby increasing model generalization. Model training utilized a transfer learning strategy, and its performance was assessed through four key indicators: accuracy, precision, recall, and F1-score. The findings demonstrate that VGG-16 achieved the most reliable outcomes, obtaining an accuracy of 0.91 and an F1-score of 0.87, outperforming ResNet-50, which reached 0.82 accuracy. All experimental data, including training and inference outputs, were stored using the InterPlanetary File System (IPFS), while each file’s Content Identifier (CID) and metadata were recorded in a blockchain-based smart contract to ensure transparency, verifiability, and data permanence. The study concludes that integrating blockchain with deep learning establishes a trustworthy and tamper-resistant framework for forest fire image classification. Future research may explore lighter CNN models and the fusion of IoT sensor data to enable adaptive and real-time fire detection.

The gearbox is one of the key components of many large mechanical transmission devices. Due to the complex working environment, the vibration signal stability of the gear box is poor, the fault feature extraction is difficult, and the fault diagnosis accuracy makes it difficult to meet the expected requirements. To solve this problem, this paper proposes a gearbox fault diagnosis method based on an optimized stacked denoising auto encoder (SDAE) and kernel extreme learning machine (KELM). Firstly, the particle swarm optimization algorithm in adaptive weight (SAPSO) was adopted to optimize the SDAE network structure, and the number of hidden layer nodes, learning rate, noise addition ratio and iteration times were adaptively obtained to make SDAE obtain the best network structure. Then, the best SDAE network structure was used to extract the deep feature information of weak faults in the original signal. Finally, the extracted fault features are fed into KELM for fault classification. Experimental results show that the classification accuracy of the proposed method can reach 97.2% under the condition of low signal-to-noise ratio, which shows the effectiveness and robustness of the proposed method compared with other diagnostic methods.

With the rapid growth in demand for security surveillance, assisted driving, and remote sensing, object detection networks with robust environmental perception and high detection accuracy have become a research focus. However, single-modality image detection technologies face limitations in environmental adaptability, often affected by factors such as lighting conditions, fog, rain, and obstacles like vegetation, leading to information loss and reduced detection accuracy. We propose an object detection network that integrates features from visible light and infrared images—IV-YOLO—to address these challenges. This network is based on YOLOv8 (You Only Look Once v8) and employs a dual-branch fusion structure that leverages the complementary features of infrared and visible light images for target detection. We designed a Bidirectional Pyramid Feature Fusion structure (Bi-Fusion) to effectively integrate multimodal features, reducing errors from feature redundancy and extracting fine-grained features for small object detection. Additionally, we developed a Shuffle-SPP structure that combines channel and spatial attention to enhance the focus on deep features and extract richer information through upsampling. Regarding model optimization, we designed a loss function tailored for multi-scale object detection, accelerating the convergence speed of the network during training. Compared with the current state-of-the-art Dual-YOLO model, IV-YOLO achieves mAP improvements of 2.8%, 1.1%, and 2.2% on the Drone Vehicle, FLIR, and KAIST datasets, respectively. On the Drone Vehicle and FLIR datasets, IV-YOLO has a parameter count of 4.31 M and achieves a frame rate of 203.2 fps, significantly outperforming YOLOv8n (5.92 M parameters, 188.6 fps on the Drone Vehicle dataset) and YOLO-FIR (7.1 M parameters, 83.3 fps on the FLIR dataset), which had previously achieved the best performance on these datasets. This demonstrates that IV-YOLO achieves higher real-time detection performance while maintaining lower parameter complexity, making it highly promising for applications in autonomous driving, public safety, and beyond.

The detection of mirrors and glass, which possess unique optical surface properties, has garnered significant attention in recent years. Due to their reflective and transparent nature, these surfaces are often difficult to distinguish from their surrounding environments, posing substantial challenges even for advanced deep learning models tasked with performing such detection. Current research primarily relies on complex network models that learn and fuse different modalities of images, such as RGB, depth, and thermal, to achieve mirror and glass detection. However, these approaches often overlook the inherent limitations in the raw data caused by sensor deficiencies when facing mirrors and glass surfaces. To address this issue, we applied mathematical and physical methods, such as three-point plane determination and steady-state heat conduction in two-dimensional planes, along with an RGB enhancement module, to reconstruct RGB, depth, and thermal data for mirrors and glass in two publicly available datasets: an RGB-D mirror detection dataset and an RGB-T glass detection dataset. Additionally, we synthesized four enhanced and ideal datasets. Furthermore, we propose a double weight Mamba fusion network (DWMFNet) that strengthens the model’s global perception of image information by extracting low-level clue weights and high-level contextual weights from the input data using the prior fusion feature extraction module (PFFE) and the deep fusion feature guidance module (DFFG). This is complemented by the Mamba module, which efficiently captures long-range dependencies, facilitating information complementarity between multi-modal features. Extensive experiments demonstrate that our data enhancement method significantly improves the model’s capability in detecting mirrors and glass surfaces.

Due to the popularity of JPEG as a compression standard, the importance of detecting manipulation in JPEG images has increased. Many data-driven approaches are implemented to detect manipulation of uncompressed scenario; however, the performance degraded significantly in re-compressed images due to lossy compression. To achieve this, a deep residual framework is designed to provide the highest-quality manipulation detection in re-compressed images (MDRNet). The framework undergoes three folds: noise residual extraction, feature extraction, and classification. Firstly, the noise residual extraction stage significantly expands the front-end detector, including three residual blocks with skip connections that can generate noise residuals by suppressing the image content and enhancing the manipulation traces. Next, two efficient residual blocks with cross feature learning strategy to obtain the deep manipulation features and fed to fully connected layers for classification. Experiments are performed on ten alterations followed by different quality factors to enhance forgery detection in the real-world scenario. Further, the proposed MDRNet achieves superior performance compared to the state-of-the-art baselines, precisely the most challenging case with lossy post-JPEG compression.