Bio: Aakash Sinha is an academic researcher from Shiv Nadar University. The author has contributed to research in topics: Tree (data structure) & Precision agriculture. The author has an hindex of 1, co-authored 4 publications receiving 11 citations.
TL;DR: A combination of spectral vegetation indices techniques has been highlighted to produce a comprehensive solution for precision agriculture using a UAV and VegNet.
Abstract: Farmers, agencies, agricultural research community and firms require access to tools to analyze and estimate stressed and productive regions to obtain higher yield. At present, this is performed manually using visual interpretation. Recently there has been some development in the detection and mapping of the stressed crop by use of hyperspectral analysis; but, there is an information gap between farmers and information about the location of the crop under stress in the given area. There is an urgent need to provide a robust solution to identify the stressed region in the agricultural area. To address this, a unique application called as VegNet (Vegetative-Network) has been developed, which aims to provide the necessary tools to detect stressed crop locations using the spectral images obtained from UAVs, and provide stressed crops condition, location and area covered by those stressed crops. In this paper, a combination of spectral vegetation indices techniques has been highlighted to produce a comprehensive solution for precision agriculture using a UAV and VegNet. This incorporates several algorithms; segmentation, Canny-edge detector, dilation, gap-filling, image extraction and locating the stressed region using spectral modelling based Graphical User Interface (GUI) application for precision agriculture, societal benefit and Environmental research.
••20 Apr 2020
TL;DR: The design and control of an autonomous amphibian all terrain six-legged robot with adaptive gait for rescue operations is described and LiDAR and camera in parallel are used in parallel to assist bot in locomotion and detect the victim.
Abstract: Nowadays robots have been inching towards living beings in terms of performance, agility, accuracy and performance. But there is one domain which is yet to come to limelight i.e. autonomous rescue robots. This involves a parallel use of robot design and control systems to get it executed. Basically, in simpler terms, there is a risk of life is involved in such scenarios and it's always hoped that a robot deployed for such operations be working with high precision and recall. So, in this paper we have described the design and control of an autonomous amphibian all terrain six-legged robot with adaptive gait for rescue operations. To fulfill this, we have used LiDAR and camera in parallel to assist bot in locomotion and detect the victim. Achieving all of this needs a significant amount of on-board processing power, but at the same time has to be compact enough. Keeping this in mind, NVIDIA Jetson Nano seems to be promising choice to get all the processing done onboard.
••06 Sep 2019
TL;DR: This study adopts a state of the art object detector Mask Region-based CNN (Mask R-CNN1), through transfer learning, for the task of tree segmentation and counting, and explores the use of a sampling technique based on Gist descriptors and Gabor filtering in order to minimize the amount of training data required.
Abstract: Monitoring tree cover in an area plays an important role in a wide range of applications and advances in UAV technology has made it feasible to capture high resolution imagery which can be used for this purpose. In this study, we adopt a state of the art object detector Mask Region-based CNN (Mask R-CNN1), through transfer learning, for the task of tree segmentation and counting. One bottleneck for the proposed task is the huge amount of data required if the model is required to be scalable to various different geographical regions. Towards this end, we explore the use of a sampling technique based on Gist descriptors and Gabor filtering in order to minimize the amount of training data required for obtaining excellent model performance across images with varied geographical features. This study was conducted across four regions in India, each having a different geographical landscape. We captured a total of 2357 images across all four regions. The final training dataset comprised of 48 images (sampled using the aforementioned method), representative of the entire dataset. Our method demonstrates high quality and scalable tree detection results.
••06 Sep 2019
TL;DR: A road network mapping framework is proposed which uses a random forest model for pixel-wise road segmentation and computer vision post-processing steps including Connected Component Analysis (CCA) and Hough Lines method for network extraction from high-resolution aerial images.
Abstract: Building and expansion of an efficient transportation network are essential for urban city advancement. However, tracking road development in an area is not an easy task as city planners do not always have access to credible information. A road network mapping framework is proposed which uses a random forest model for pixel-wise road segmentation. Road detection is followed by computer vision post-processing steps including Connected Component Analysis (CCA) and Hough Lines method for network extraction from high-resolution aerial images. The custom dataset used consists of images collected from an urban settlement in India.
TL;DR: An Internet of Things (IoT) assisted Unmanned Aerial Vehicle (UAV) based rice pest detection model using Imagga cloud is proposed to identify the pests in the rice during its production in the field and attempts to minimize the wastage of rice During its production by monitoring the pests at regular intervals.
Abstract: Rice is a very essential food for the survival of human society. Most of the people focus on production of rice for their financial gain as well as their survival in the society. Rice production means a lot, not only for the farmers, but also for the entire human society However, it is very difficult to protect the rice during and after the production due to several reasons, such as natural calamities, heavy rain fall, flood, earthquakes, damage of rice due to pests, etc. Damage of rice can occur during production and after the production due to several pests. So, it is very much essential to identify the pests in the rice so that preventive measures can be taken for its protection. In this paper, an Internet of Things (IoT) assisted Unmanned Aerial Vehicle (UAV) based rice pest detection model using Imagga cloud is proposed to identify the pests in the rice during its production in the field. The IoT assisted UAV focuses on artificial intelligence (AI) mechanism and Python programming paradigm for sending the rice pest images to the Imagga cloud and providing the pest information. The Imagga cloud detects the pest by finding the confidence values with the tags. The tag represents the object in that image. The tag with maximum confidence value and beyond threshold is selected as the target tag to identify the pest. If pest is detected then the information is sent to the owner for further actions. The proposed method can able to identify any kind of the pest that affects the rice during production. Alternatively, this paper attempts to minimize the wastage of rice during its production by monitoring the pests at regular intervals.
TL;DR: In this paper, a review of the technical, legal, and software-algorithmic limitations of intelligent unmanned aerial vehicle technology (IUAVT) and modern approaches aimed at overcoming these limitations is presented.
Abstract: The use of unmanned aerial vehicles (UAVs) in various spheres of human activity is a promising direction for countries with very different types of economies. This statement refers to resource-rich economies as well. The peculiarities of such countries are associated with the dependence on resource prices since their economies present low diversification. Therefore, the employment of new technologies is one of the ways of increasing the sustainability of such economy development. In this context, the use of UAVs is a prospect direction, since they are relatively cheap, reliable, and their use does not require a high-tech background. The most common use of UAVs is associated with various types of monitoring tasks. In addition, UAVs can be used for organizing communication, search, cargo delivery, field processing, etc. Using additional elements of artificial intelligence (AI) together with UAVs helps to solve the problems in automatic or semi-automatic mode. Such UAV is named intelligent unmanned aerial vehicle technology (IUAVT), and its employment allows increasing the UAV-based technology efficiency. However, in order to adapt IUAVT in the sectors of economy, it is necessary to overcome a range of limitations. The research is devoted to the analysis of opportunities and obstacles to the adaptation of IUAVT in the economy. The possible economic effect is estimated for Kazakhstan as one of the resource-rich countries. The review consists of three main parts. The first part describes the IUAVT application areas and the tasks it can solve. The following areas of application are considered: precision agriculture, the hazardous geophysical processes monitoring, environmental pollution monitoring, exploration of minerals, wild animals monitoring, technical and engineering structures monitoring, and traffic monitoring. The economic potential is estimated by the areas of application of IUAVT in Kazakhstan. The second part contains the review of the technical, legal, and software-algorithmic limitations of IUAVT and modern approaches aimed at overcoming these limitations. The third part—discussion—comprises the consideration of the impact of these limitations and unsolved tasks of the IUAVT employment in the areas of activity under consideration, and assessment of the overall economic effect.
••01 Sep 2020
TL;DR: A unique and innovative technique to calculate the optimum location of spray points required for a particular stressed region is reported, which is divided into many circular divisions with its center being a spray point of the stressed region.
Abstract: This research paper focuses on providing an algorithm by which (Unmanned Aerial Vehicles) UAVs can be used to provide optimal routes for agricultural applications such as, fertilizers and pesticide spray, in crop fields. To utilize a minimum amount of inputs and complete the task without a revisit, one needs to employ optimized routes and optimal points of delivering the inputs required in precision agriculture (PA). First, stressed regions are identified using VegNet (Vegetative Network) software. Then, methods are applied for obtaining optimal routes and points for the spraying of inputs with an autonomous UAV for PA. This paper reports a unique and innovative technique to calculate the optimum location of spray points required for a particular stressed region. In this technique, the stressed regions are divided into many circular divisions with its center being a spray point of the stressed region. These circular divisions would ensure a more effective dispersion of the spray. Then an optimal path is found out which connects all the stressed regions and their spray points. The paper also describes the use of methods and algorithms including travelling salesman problem (TSP)-based route planning and a Voronoi diagram which allows applying precision agriculture techniques.
TL;DR: In this paper, the main problems hindering the agricultural development in the arid and semi-arid regions of the world have been identified, and many previous studies of soil salinization monitoring failed to cons...
Abstract: Soil salinization is one of the main problems hindering the agricultural development in the arid and semi-arid regions. However, many previous studies of soil salinization monitoring failed to cons...
••01 Jan 2021
TL;DR: The main conclusion of this chapter is to make aware about the growing GPS applications and evolution of SMART farming, that is, wisely employing Internet for precision applications.
Abstract: Monitoring and performing agricultural practices over a large spatial coverage often require advanced and accurate positional information in order to optimize the operational costs as well as reduce estimated time of completion. Agricultural practices with large farms are challenging to operate from remote sensing until accurate positional information is not available, which necessitates the use of Global Positioning System (GPS) for acquiring sample position using Global Navigation Satellite System (GNSSs). Thus, development of positional accuracies with the help of GNSS signals has boosted up the involvement of GPS-based instruments in precision agriculture (PA). It has opened the wide door for the implementation of GPS in the PA, as per user needs and requirements. Furthermore, GPS instruments have been evolved with time, and nowadays advanced GPS instruments are in the market and can be operated via mobile with any operating systems, i.e., iOS, Android, or Windows. Availability of GPS signals in several instruments or equipment has been looked as the market opportunity and increasing trends in PA resulting in innovations of techniques for route optimization for optimal use of fertilizer spray and related activities in agricultural practices transforming to new look as SMART farming. The main conclusion of this chapter is to make aware about the growing GPS applications and evolution of SMART farming, that is, wisely employing Internet for precision applications.