Abstract Owing to the recent technological innovations, unmanned aerial vehicles (UAVs) are progressively employed in various civil and military applications, including healthcare. This requires estimating an optimum route under various real‐world complexities, such as non‐uniform obstacles. However, most of the reported work considers only uniform obstacles as an object, which limit their practical applicability. Hence, Archimedes optimization algorithm (AOA) is examined to overcome this limitation. Further, it is observed that many a time, AOA over‐exploits the search space, resulting in higher computational time. Therefore, the present work fuses AOA with grey wolf optimizer (GWO) to improve the convergence capability. Also, reinforcement learning (RL) is employed to intelligently switch between the exploration and exploitation phases. The efficacy of the developed algorithm is statistically analysed and validated against various metaheuristics on several benchmark functions. The simulated results verified that the developed RLGA provides optimal or near‐optimal solutions more efficiently relative to other metaheuristics. Moreover, it also affirms the hypothesis that the proposed modifications significantly improve the convergence speed of AOA. Finally, the appropriateness of RLGA is tested and validated by rigorous experimentation on real‐world 3D‐route estimation problems for UAVs. The simulated results reveal that RLGA produces a flyable path with 51.46%, 62.06%, and 70.42% lesser cost than RLGWO, AOA, and GWO, respectively. This ensures the employability of RLGA for efficient medical assistance in minimum time‐, energy‐, and transportation‐cost with safe and smooth UAV auto‐navigation for developing drone doctors.

Abstract Siamese‐based trackers have received global recognition for target tracking. However, these trackers employ batch‐normalized networks for feature extraction, which has been sensitive to batch size and hard to replicate on different hardware. Therefore, to meliorate tracking performance and effectively address this issue, the present work proposes a Normalization free Siamese (NfS) tracker by introducing normalization‐free networks in target tracking. The developed NfS has been trained end‐to‐end with large‐scale datasets such as COCO, TrackingNet, LaSOT, VID, DET, and GOT10k. Extensive experimentation has been carried out on six challenging benchmark datasets (OTB100, LaSOT, VOT2018, VOT2019, UAV123, and GOT10k), revealing that NfS ensures comparable performance with state‐of‐the‐art (SOTA) trackers on most of the benchmarks. It pushed the performance bar by a minimum of 2.88% and 2.37% on UAV123 for both precision and success scores. Also, it overshadows the compared trackers by a significant minimum margin of 11.88% and 8.14% on the LaSOT for similar metrics, demonstrating the higher discrimination capability of the NfS tracker for both natural and aerial target tracking tasks.

Image classification has become the backbone of computer vision in recent times. Hierarchical image classification has been a scarcely exploited field, particularly in household images. Although many convolution and transformer learning models have been introduced for image classification, the fusion models exhibit much better performance in image classification. The potential of hierarchical image classification for household robotics has not yet been explored. Therefore, we propose a Trans-convo-former net for the hierarchical prediction of household images. The fine class refers to the class of the object identified, and the coarse class refers to the object’s location. This process facilitates the path-planning stage of household robotics. Trans-convo-former net employs self-attention-based encoders with intermittent convolution layers to extract global and local features from the image. The model is observed to outperform the state-of-the-art models applied for hierarchical image classification. Trans-convo-former net is proposed in two versions namely; big and small. The model is compared to another fusion model as well. The performance of the proposed model is found to be the most optimum. An ablation study is also performed with different numbers of transconvoformers, attention layers, and epochs to find the best-performing parameters for the proposed model.

With the introduction of Web 2.0, there has been an extreme increase in the popularity of social bookmarking systems and folksonomies. In this paper, our motive is to develop a recommender system that is based on user assigned tags and content present on web pages. Although the tag recommendations in social tagging systems can be very accurate and personalized, there exists an issue of risk to the privacy of user's profile, since the social tags are given by a user expose his preferences to other users in contact. To overcome this problem, we have incorporated obfuscation privacy strategies with the well-known Delicious dataset in social tagging based recommender system. We have applied the popular supervised machine-learning algorithm, K-Nearest Neighbours classifier to the dataset that recommends relevant tags to the user. Privacy has been introduced in our tag-based recommender system by hiding some of the necessary tags, bookmarks of a user and replacing them with some random tags and bookmarks. Our experiment results indicate that the recommender system being implemented is highly efficient in terms recall and privacy measure for different values of k. The results and comparisons indicate that we have successfully employed an effective tag recommender system, which also protects the user's privacy without any significant fall in the quality of recommendation.

This paper presents a fuzzy system for edge detection, using smallest univalue segment assimilating nucleus (USAN) principle and bacterial foraging algorithm (BFA). The proposed algorithm fuzzifies the USAN area obtained from the original image, using a USAN area histogram-based Gaussian membership function. A parametric fuzzy intensification operator (FINT) is proposed to enhance the weak edge information, which results in another fuzzy set. The fuzzy measures, i.e., fuzzy edge quality factor and sharpness factor, are defined on fuzzy sets. The BFA is used to optimize the parameters involved in the fuzzy membership function and the FINT. The fuzzy edge map is obtained using optimized parameters. The adaptive thresholding is used to defuzzify the fuzzy edge map to obtain a binary edge map. The experimental results are analyzed qualitatively and quantitatively. The quantitative measures, i.e., Pratt's figure of merit, Cohen' Kappa, Shannon's entropy, and edge strength similarity-based edge quality metric, are used. The quantitative results are statistically analyzed using t-test. The proposed algorithm outperforms many of the traditional and state-of-the-art edge detectors.

This paper presents contrast enhancement algorithms based on fuzzy contextual information of the images. We introduce fuzzy similarity index and fuzzy contrast factor to capture the neighborhood characteristics of a pixel. A new histogram, using fuzzy contrast factor of each pixel is developed, and termed as the fuzzy dissimilarity histogram (FDH). A cumulative distribution function (CDF) is formed with normalized values of FDH and used as a transfer function to obtain the contrast enhanced image. The algorithm gives good contrast enhancement and preserves the natural characteristic of the image. In order to develop a contextual intensity transfer function, we introduce a fuzzy membership function based on fuzzy similarity index and coefficient of variation of the image. The contextual intensity transfer function is designed using the fuzzy membership function to achieve final contrast enhanced image. The overall algorithm is referred as the fuzzy contextual contrast-enhancement (FCCE) algorithm. The proposed algorithms are compared with conventional and state-of-art contrast enhancement algorithms. The quantitative and visual assessment of the results is performed. The results of quantitative measures are statistically analyzed using t-test. The exhaustive experimentation and analysis show the proposed algorithm efficiently enhances contrast and yields in natural visual quality images.

This study presents a new contrast‐enhancement approach called entropy‐based dynamic sub‐histogram equalisation. The proposed algorithm performs a recursive division of the histogram based on the entropy of the sub‐histograms. Each sub‐histogram is divided recursively into two sub‐histograms with equal entropy. A stopping criterion is proposed to achieve an optimum number of sub‐histograms. A new dynamic range is allocated to each sub‐histogram based on the entropy and number of used and missing intensity levels in the sub‐histogram. The final contrast‐enhanced image is obtained by equalising each sub‐histogram independently. The proposed algorithm is compared with conventional as well as state‐of‐the‐art contrast‐enhancement algorithms. The quantitative results for a large image data set are statistically analysed using a paired t ‐test. The quantitative and visual assessment shows that the proposed algorithm outperforms most of the existing contrast‐enhancement algorithms. The proposed algorithm results in natural‐looking, good contrast images with almost no artefacts.