Search

Wheat stripe rust disease (WRD) is extremely detrimental to wheat crop health, and it severely affects the crop yield, increasing the risk of food insecurity. Manual inspection by trained personnel is carried out to inspect the disease spread and extent of damage to wheat fields. However, this is quite inefficient, time-consuming, and laborious, owing to the large area of wheat plantations. Artificial intelligence (AI) and deep learning (DL) offer efficient and accurate solutions to such real-world problems. By analyzing large amounts of data, AI algorithms can identify patterns that are difficult for humans to detect, enabling early disease detection and prevention. However, deep learning models are data-driven, and scarcity of data related to specific crop diseases is one major hindrance in developing models. To overcome this limitation, in this work, we introduce an annotated real-world semantic segmentation dataset named the NUST Wheat Rust Disease (NWRD) dataset. Multileaf images from wheat fields under various illumination conditions with complex backgrounds were collected, preprocessed, and manually annotated to construct a segmentation dataset specific to wheat stripe rust disease. Classification of WRD into different types and categories is a task that has been solved in the literature; however, semantic segmentation of wheat crops to identify the specific areas of plants and leaves affected by the disease remains a challenge. For this reason, in this work, we target semantic segmentation of WRD to estimate the extent of disease spread in wheat fields. Sections of fields where the disease is prevalent need to be segmented to ensure that the sick plants are quarantined and remedial actions are taken. This will consequently limit the use of harmful fungicides only on the targeted disease area instead of the majority of wheat fields, promoting environmentally friendly and sustainable farming solutions. Owing to the complexity of the proposed NWRD segmentation dataset, in our experiments, promising results were obtained using the UNet semantic segmentation model and the proposed adaptive patching with feedback (APF) technique, which produced a precision of 0.506, recall of 0.624, and F1 score of 0.557 for the rust class. [ABSTRACT FROM AUTHOR]

We propose a novel hybrid approach that fuses traditional computer vision techniques with deep learning models to detect figures and formulas from document images. The proposed approach first fuses the different computer vision based image representations, i.e., color transform, connected component analysis, and distance transform, termed as Fi-Fo image representation. The Fi-Fo image representation is then fed to deep models for further refined representation-learning for detecting figures and formulas from document images. The proposed approach is evaluated on a publicly available ICDAR-2017 Page Object Detection (POD) dataset and its corrected version. It produces the state-of-the-art results for formula and figure detection in document images with an f1-score of 0.954 and 0.922 , respectively. Ablation study results reveal that the Fi-Fo image representation helps in achieving superior performance in comparison to raw image representation. Results also establish that the hybrid approach helps deep models to learn more discriminating and refined features. [ABSTRACT FROM AUTHOR]

Abstract Computer vision and image processing approaches for automatic underwater fish detection are gaining attention of marine scientists as quicker and low-cost methods for estimating fish biomass and assemblage in oceans and fresh water bodies. However, the main challenge that is encountered in unconstrained underwater imagery is poor luminosity, turbidity, background confusion and foreground camouflage that make conventional approaches compromise on their performance due to missed detections or high false alarm rates. Gaussian Mixture Modelling is a powerful approach to segment foreground fish from the background objects through learning the background pixel distribution. In this paper, we present an algorithm based on Gaussian Mixture Models together with Pixel-Wise Posteriors for fish detection in complex background scenarios. We report the results of our method on the benchmark Complex Background dataset that is extracted from Fish4Knowledge repository. Our proposed method yields an F-score of 84.3%, which is the highest score reported so far on the aforementioned dataset for detecting fish in an unconstrained environment. Highlights • Automatic fish sampling is critical to estimate the biomass and abundance of fish in water bodies. • A method using pixel-wise posteriors on Gaussian mixture modelling is proposed for fish detection in underwater videos. • A benchmark dataset with different categories of underwater environments is used for the evaluation of the proposed approach. • Favourable results are reported using the proposed approach, outperforming the current state-of-the-art. • The proposed algorithm is computationally efficient, producing real-time outcome. [ABSTRACT FROM AUTHOR]

There is a need for automatic systems that can reliably detect, track and classify fish and other marine species in underwater videos without human intervention. Conventional computer vision techniques do not perform well in underwater conditions where the background is complex and the shape and textural features of fish are subtle. Data-driven classification models like neural networks require a huge amount of labelled data, otherwise they tend to over-fit to the training data and fail on unseen test data which is not involved in training. We present a state-of-the-art computer vision method for fine-grained fish species classification based on deep learning techniques. A cross-layer pooling algorithm using a pre-trained Convolutional Neural Network as a generalized feature detector is proposed, thus avoiding the need for a large amount of training data. Classification on test data is performed by a SVM on the features computed through the proposed method, resulting in classification accuracy of 94.3% for fish species from typical underwater video imagery captured off the coast of Western Australia. This research advocates that the development of automated classification systems which can identify fish from underwater video imagery is feasible and a cost-effective alternative to manual identification by humans. [ABSTRACT FROM AUTHOR]

Recognizing semantic category of objects and scenes captured using vision-based sensors is a challenging yet essential capability for mobile robots and UAVs to perform high-level tasks such as long-term autonomous navigation. However, extracting discriminative features from multi-modal inputs, such as RGB-D images, in a unified manner is non-trivial given the heterogeneous nature of the modalities. We propose a deep network which seeks to construct a joint and shared multi-modal representation through bilinearly combining the convolutional neural network (CNN) streams of the RGB and depth channels. This technique motivates bilateral transfer learning between the modalities by taking the outer product of each feature extractor output. Furthermore, we devise a technique for multi-scale feature abstraction using deeply supervised branches which are connected to all convolutional layers of the multi-stream CNN. We show that end-to-end learning of the network is feasible even with a limited amount of training data and the trained network generalizes across different datasets and applications. Experimental evaluations on benchmark RGB-D object and scene categorization datasets show that the proposed technique consistently outperforms state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

There is an urgent need for the development of sampling techniques which can provide accurate and precise count, size, and biomass data for fish. This information is essential to support the decision-making processes of fisheries and marine conservation managers and scientists. Digital video technology is rapidly improving, and it is now possible to record long periods of high resolution digital imagery cost effectively, making single or stereo-video systems one of the primary sampling tools. However, manual species identification, counting, and measuring of fish in stereo-video images is labour intensive and is the major disincentive against the uptake of this technology. Automating species identification using technologies developed by researchers in computer vision and machine learning would transform marine science. In this article, a new paradigm of image set classification is presented that can be used to achieve improved recognition rates for a number of fish species. State-of-the-art image set construction, modelling, and matching algorithms from computer vision literature are discussed with an analysis of their application for automatic fish species identification. It is demonstrated that these algorithms have the potential of solving the automatic fish species identification problem in underwater videos captured within unconstrained environments. [ABSTRACT FROM AUTHOR]

This paper evaluates the degree of saliency of texts in natural scenes using visual saliency models. A large scale scene image database with pixel level ground truth is created for this purpose. Using this scene image database and five state-of-the-art models, visual saliency maps that represent the degree of saliency of the objects are calculated. The receiver operating characteristic curve is employed in order to evaluate the saliency of scene texts, which is calculated by visual saliency models. A visualization of the distribution of scene texts and non-texts in the space constructed by three kinds of saliency maps, which are calculated using Itti's visual saliency model with intensity, color and orientation features, is given. This visualization of distribution indicates that text characters are more salient than their non-text neighbors, and can be captured from the background. Therefore, scene texts can be extracted from the scene images. With this in mind, a new visual saliency architecture, named hierarchical visual saliency model, is proposed. Hierarchical visual saliency model is based on Itti's model and consists of two stages. In the first stage, Itti's model is used to calculate the saliency map, and Otsu's global thresholding algorithm is applied to extract the salient region that we are interested in. In the second stage, Itti's model is applied to the salient region to calculate the final saliency map. An experimental evaluation demonstrates that the proposed model outperforms Itti's model in terms of captured scene texts. [ABSTRACT FROM AUTHOR]

Abstract: Recent advances in computer vision on the one hand, and imaging technologies on the other hand, have opened up a number of interesting possibilities for robust 3D scene labeling. This paper presents contributions in several directions to improve the state-of-the-art in RGB-D scene labeling. First, we present a novel combination of depth and color features to recognize different object categories in isolation. Then, we use a context model that exploits detection results of other objects in the scene to jointly optimize labels of co-occurring objects in the scene. Finally, we investigate the use of social media mining to develop the context model, and provide an investigation of its convergence. We perform thorough experimentation on both the publicly available RGB-D Dataset from the University of Washington as well as on the NYU scene dataset. An analysis of the results shows interesting insights about contextual object category recognition, and its benefits. [Copyright &y& Elsevier]

In contrast to prior experimental work, our results support the conclusion that RXYC can perform well after marginal noise removal. However, marginal noise removal on page images like those found in UW3 remains a hard problem and it therefore remains an open question whether RXYC can actually achieve competitive performance on such databases. [ABSTRACT FROM AUTHOR]

• Gait analysis is great avenue for person identification in an un-intrusive manner. • The spatio-temporal aspects of a human gait can be captured through a 3D CNN. • Bayesian optimization is used to tweak the hyperparameters of the architecture. Systems based on physiological biometrics are ubiquitous but requires subject cooperation or high resolution to capture. Gait recognition is a great avenue for identification and authentication due to uniqueness of individual stride in an un-intrusive manner. Machine vision systems have been designed to capture the uniqueness of stride of a specific person but factors such as change in speed of stride, view point, clothes and carrying accessories make gait recognition challenging and open to innovation. Our proposed approach attempts to tackle these problems by capturing the spatio-temporal features of a gait sequence by training a 3D convolutional deep neural network (3D CNN). The proposed 3D CNN architecture tackles gait identification by employing holistic approach in the form of gait energy images (GEI) which is a condensed representation capturing the shape and motion characteristics of the the human gait. The network was evaluated on two of the largest publicly available datasets with substantial gender and age diversity; OULP and CASIA-B. Optimization strategies were explored to tune the hyper-parmeters and improve the performance of the 3D CNN network. The optimized 3D CNN and the GEI were effectively able to capture the unique characteristics of the gait cycle of an individual irrespective of the challenging covariates. State of the art results achieved on the multi-views and multiple carrying conditions of the subjects belonging to CASIA-B dataset demonstrating the efficacy of our proposed algorithm. [ABSTRACT FROM AUTHOR]