Features for detecting smoke in laparoscopic videos

Smoke in laparoscopic videos usually appears due to the use of electrocautery when cutting or coagulating tissues. Therefore, detecting smoke can be used for event-based annotation in laparoscopic surgeries by retrieving the events associated with the electrocauterization. Furthermore, smoke detection can also be used for automatic smoke removal. However, detecting smoke in laparoscopic video is a challenge because of the changeability of smoke patterns, the moving camera and the different lighting conditions. In this paper, we present a video-based smoke detection algorithm to detect smoke of different densities such as fog, low and high density in laparoscopic videos. The proposed method depends on extracting various visual features from the laparoscopic images and providing them to support vector machine (SVM) classifier. Features are based on motion, colour and texture patterns of the smoke. We validated our algorithm using experimental evaluation on four laparoscopic cholecystectomy videos. These four videos were manually annotated by defining every frame as smoke or non-smoke frame. The algorithm was applied to the videos by using different feature combinations for classification. Experimental results show that the combination of all proposed features gives the best classification performance. The overall accuracy (i.e. correctly classified frames) is around 84%, with the sensitivity (i.e. correctly detected smoke frames) and the specificity (i.e. correctly detected non-smoke frames) are 89% and 80%, respectively.

A method of early smoke detection in video using swaying and diffusion feature is presented in this paper. Firstly, in view of early smoke's swaying feature, choquet fuzzy integral was adopted to extract dynamic regions from video frames, and then, a swaying identification algorithm based on centroid calculation was used to distinguish candidate smoke region from other dynamic regions. Secondly, smoke diffusion makes different textures between the bottom region and the top region of smoke. This unique feature was used to differentiate smoke from other candidate smoke regions by Gray Level Co-occurrence Matrix. Experiments show that the proposed method is effective, robust, and has a performance of earlier smoke alarm. The processing rate of the smoke detection method achieves 25 frames per second with an image size of 320 × 240 pixels.

Video-based smoke detection has a very wide range of applications. In this paper, we propose a smoke detection method based on the structural similarity and complexity of image. The background of image blurred by smoke causes the degradation of image quality, similar to adding noise to the image, which is very different from the background obscured by objects. Thus the structural similarity of image, usually for objective quality assessment of image, can be utilized to detect smoke qualitatively. The value of structural similarity index of image is affected by the complexity of image. We extract the texture features of image based on the gray level co-occurrence matrix and use the weighted sum of the second moment, the contrast, the inverse moment, the entropy and the correlation of image to determine the complexity of image. On this basis, we propose a method based on the structural similarity index of image determined by the image complexity for qualitative and quantitative smoke detection, and develop a DSPs system of video smoke detection based on the DM6437 EVM made by Texas Instruments. Experimental results show that the values of the structural similarity index determined by complexity of image are in good agreement with the results of the obscuration coefficient measured from optical smoke density meter.

Detection of fire and smoke in video is of practical and theoretical interest. In this paper, we propose the use of optimal mass transport (OMT) optical flow as a low-dimensional descriptor of these complex processes. The detection process is posed as a supervised Bayesian classification problem with spatio-temporal neighborhoods of pixels;feature vectors are composed of OMT velocities and R,G,B color channels. The classifier is implemented as a single-hidden-layer neural network. Sample results show probability of pixels belonging to fire or smoke. In particular, the classifier successfully distinguishes between smoke and similarly colored white wall, as well as fire from a similarly colored background.

Smoke detection in video using wavelets and support vector machines

An efficient smoke detection algorithm on color video sequences obtained from a stationary camera is proposed. Our algorithm considers dynamic and static features of smoke and composed of basic steps: preprocessing; slowly moving areas and pixels segmentation in a current input frame based on adaptive background subtraction; merge slowly moving areas with pixels into blobs; classification of the blobs obtained before. We use adaptive background subtraction at a stage of moving detection. Moving blobs classification is based on optical flow calculation, Weber contrast analysis and takes into account primary direction of smoke propagation. Real video surveillance sequences are used for smoke detection with utilization our algorithm. A set of experimental results are presented in the paper.

As an emerging development in the digital technology era, video processing is useful in a wide range of applications. In the current paper, an algorithm is proposed which is useful for smoke detection in video processing. The algorithm quickly detects fire by eliminating common interruptions like noise, overlapping due to the collision, etc. The proposed algorithm is composed of several techniques such as Haar feature, Bhattacharya distance method, SIFT descriptors, Gabor wavelets approach and SVM classifier to identify the smoke by video processing. Foreground object is identified using a moving object algorithm by predicting the movement of smoke in stable images. The implementation has been carried out in MATLAB.

Semantic segmentation of anatomical structures in laparoscopic videos is a crucial task to enable the development of new computer-assisted systems that can assist surgeons during surgery. However, this is a difficult task due to artifacts and similar visual characteristics of anatomical structures on the laparoscopic videos. Recently, deep learning algorithms have been showed promising results on the segmentation of laparoscopic instruments. However, due to the lack of large public datasets for semantic segmentation of anatomical structures, there are only a few studies on this task. In this work, we evaluate the performance of five networks, namely U-Net, U-Net++, DynUNet, UNETR and DeepLabV3+, for segmentation of laparoscopic cholecystectomy images from the recently released CholecSeg8k dataset. To the best of our knowledge, this is the first benchmark performed on this dataset. Training was performed with dice loss. The networks were evaluated on segmentation of 8 anatomical structures and instruments, performance was quantified through the dice coefficient, intersection over union, recall, and precision. Apart from the U-Net, all networks obtained scores similar to each other, with the U-Net++ being the network with the best overall score with a mean Dice value of 0.62. Overall, the results show that there is still room for improvement in the segmentation of anatomical structures from laparoscopic videos. Clinical Relevance- The results of this study show the potential of deep neural networks for the segmentation of anatomical structures in laparoscopic images which can later be incorporated into computer-aided systems for surgeons.

PurposeThis study aims to enhance surgical safety by developing a method for vascular segmentation in laparoscopic surgery videos with limited visibility. We introduce an adaptive sensitivity-fisher regularization (ASFR) approach to adapt neural networks, initially trained on non-medical datasets, for vascular segmentation in laparoscopic videos.MethodsOur approach utilizes heterogeneous transfer learning by integrating fisher information and sensitivity analysis to mitigate catastrophic forgetting and overfitting caused by limited annotated data in laparoscopic videos. We calculate fisher information to identify and preserve critical model parameters while using sensitivity measures to guide adjustment for new task.ResultsThe fine-tuned models demonstrated high accuracy in vascular segmentation across various complex video sequences, including those with obscured vessels. For both invisible and visible vessels, our method achieved an average Dice score of 41.3. In addition to outperforming traditional transfer learning approaches, our method exhibited strong adaptability across multiple advanced video segmentation architectures. ConclusionThis study introduces a novel heterogeneous transfer learning approach, ASFR, which significantly enhances the precision of vascular segmentation in laparoscopic videos. ASFR effectively addresses critical challenges in surgical image analysis and paves the way for broader applications in laparoscopic surgery, promising improved patient outcomes and increased surgical efficiency.

Notice of Violation of IEEE Publication Principles<br><br>"Effective Visual Fire Detection in Video Sequences Using Probabilistic Approach"<br>by P. Jenifer<br>in the 2011 International Conference on Emerging Trends in Electrical and Computer Technology (ICETECT), 2011, pp. 870 – 875.<br><br>After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles.<br><br>This paper contains significant portions of original text from the paper cited below. The original text was copied with insufficient attribution (including appropriate references to the original author(s) and/or paper title) and without permission.<br><br>Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following article:<br><br>"A Probabilistic Approach for Vision-Based Fire Detection in Videos"<br>by Paulo Vinicius Koerich Borges and Ebroul Izquierdo<br>in IEEE Transactions on Circuits and Systems for Video Technology Vol. 5, No. 5, 2010, pp. 721 – 731.<br><br> <br/> The objective is to develop a probabilistic approach for vision-based fire detection in videos. The proposed method analyzes the frame-to-frame changes of specific low-level features describing potential fire regions. These features are color, area size, surface coarseness, boundary roughness, and skewness within estimated fire regions. Because of flickering and random characteristics of fire, these features are powerful discriminants. The behavioral change of each one of these features is evaluated, and the results are then combined according to the Bayes classifier for robust fire recognition. Temporal matching concept is used to reduce the computational complexity and also to allow fast processing of videos. Early vision-based fire detection techniques target surveillance applications with static cameras and consequently reasonably controlled or static background. In contrast, the proposed method can be applied not only to surveillance but also to automatic video classification for retrieval of fire catastrophes in databases of newscast content.

Fire and smoke are common sight at mines and could be catastrophic for humans working there. Our paper focuses on an alert mechanism that is built based on detection and validation of smoke from mines. We propose a computer vision based model that is robust enough to detect presence of smoke and the direction of motion of smoke. This research paper proposes a smoke detection model integrated with Unmanned Aerial Vehicle (UAV). The model focuses on smoke detection that leads to early detection of fire. The model works on the basis of image processing. The distinguishing feature of our model is the dynamic and real time processing. Here the system tracks the dynamic environment in the mining areas using UAVs featured with cameras. The real time captured video frames are calibrated to overcome distortion considering the radial and tangential factors. The calibrated frame thus obtained is further processed to get the Region of Interest (ROI) based on the spatial Hue Saturation Value (HSV) colouring model. Each pixel of the frame is then compared with colour range of smoke using opencv functions. The matched ROI is de-noised using Non-local means De-nosing algorithm to avoid unnecessary colours. These filtered frames are then processed concurrently to identify the pattern of change in motion. Based on this pattern the ROI is classified as either smoke or no smoke. With the analysis of turbulence in each pixel the intensity of smoke is detected. The experiment is conducted with-1) Prerecorded smoke video clippings. 2) Real time video captured in the camera. The results turned out to be positive in both the test cases. So, the model works quite efficiently with both recorded and real time video. Key Terms: UAV, ROI, HSV, De-noising algorithm, pattern matching

The quality of fruit production is very important because it is related to the value of sales. Data from the Directorate General of Horticulture at the Ministry of Agriculture in 2017 showed that 94,3% of the total yield of citrus fruits is a type of tangerine. In the classification of the quality, the visual observation process is strongly influenced by subjectivity so that in certain conditions such as tired eyes and the number of oranges that want to classify too many the process can be inconsistent and also take a long time. Therefore, a technology is needed to accelerate the classification process and make it more objective. This study combines the Gray level Co-occurrence Matrix (GLCM) method for texture, Hue, Saturation, Value (HSV) features for color features and the k-Nearest Neighbor (k-NN) classification method. The data used were 60 images of rotten tangerines and 60 images of not rotten tangerines divided using a 4-fold cross-validation method to find the best combination of data training and data testing. 3 main processes will be carried out, namely preprocessing, feature extraction and classification. This study produced the highest accuracy of 80% from the combined of GLCM and HSV features extraction with value k = 5 for k-NN .

The nature of endoscopy as a type of minimally invasive surgery (MIS) requires surgeons to perform complex operations by merely inspecting a live camera feed. Inherently, a successful intervention depends upon ensuring proper working conditions, such as skillful camera handling, adequate lighting and removal of confounding factors, such as fluids or smoke. The latter is an undesirable byproduct of cauterizing tissue and not only constitutes a health hazard for the medical staff as well as the treated patients, it can also considerably obstruct the operating physician's field of view. Therefore, as a standard procedure the gaseous matter is evacuated by using specialized smoke suction systems that typically are activated manually whenever considered appropriate. We argue that image-based smoke detection can be employed to undertake such a decision, while as well being a useful indicator for relevant scenes in post-procedure analyses. This work represents a continued effort to previously conducted studies utilizing pre-trained convolutional neural networks (CNNs) and threshold-based saturation analysis. Specifically, we explore further methodologies for comparison and provide as well as evaluate a public dataset comprising over 100K smoke/non-smoke images extracted from the Cholec80 dataset, which is composed of 80 different cholecystectomy procedures. Having applied deep learning to merely 20K images of a custom dataset, we achieve Receiver Operating Characteristic (ROC) curves enclosing areas of over 0.98 for custom datasets and over 0.77 for the public dataset. Surprisingly, a fixed threshold for saturation-based histogram analysis still yields areas of over 0.78 and 0.75.

Leaf canopy area is a fundamental crop growth characteristic that encompasses the spatial area covered by plants. However, non-destructive and automatic computation of lettuce canopy area is still open research. This study presents a vision-based system with color space thresholding and machine learning models in measuring the photosynthetic productivity of aquaponic lettuce based on canopy area derived from the numerical image textural features of Haralick and gray level co-occurrence matrix (GLCM). Lettuce images on different growth stages with varying photosynthetic pigment intensities and geometrical structures are extracted with contrast, correlation, energy, homogeneity, entropy, variance, and information measure of correlations 1 and 2 features. For multi-band color space thresholding, CIELab bested RGB, HSV, and YCbCr colour spaces in segmenting the lettuce plant with sensitivity and specificity measures of 94.77% and 97.16% respectively. For measuring the lettuce canopy area, RMSE was recorded as 50.23% for fitness function neural network (FFNN), 20.46% for radial basis function neural network (RBFNN), 15.11% for exact radial basic function neural network (RBEFNN) and 13.54% for generalized regression neural network (GRNN). Comparative analysis revealed that the two-hidden layer GRNN model with 0.09 spread value and 240 hidden neurons bested other machine learning models in terms of RMSE without overfitting.

Many people are being affected by eczema around the world. In the Philippines, the most common types of eczema are atopic dermatitis, contact dermatitis, and nummular dermatitis. This study covered these three types and detected them by applying image processing techniques, Gray Level Co-occurrence Matrix, and the classifier Support Vector Machine. The designed prototype is to capture a section of the skin where eczema can be present and send the image to the software for skin region detection, eczema region detection, and feature extractions. In skin region detection, the YCbCr color model identifies the skin's color to discard the non-skin pixels and detect the skin pixels, allowing isolation of those pixels. The eczema region detection uses the CIELAB color model and K-means clustering to extract eczema on the image. The feature extractions have color features composed of RGB, HSV, and YCbCr color models and texture features consisting of contrast, homogeneity, energy, and correlation of GLCM. Then the software will classify the acquired image as healthy, atopic, contact, or nummular using SVM. Next to the testing process, the results are obtained and plotted in a confusion matrix. After analyzing the results, the computed overall accuracy of the system was 83.33%.