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.
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.
Ro-Boat is an autonomous river cleaning intelligent robot incorporating mechanical design and computer vision algorithm to achieve autonomous river cleaning and provide a sustainable environment. Ro-boat is designed in a modular fashion with design details such as mechanical structural design, hydrodynamic design and vibrational analysis. It is incorporated with a stable mechanical system with air and water propulsion, robotic arms and solar energy source and it is proceed to become autonomous by using computer vision. Both “HSV Color Space” and “SURF” are proposed to use for measurements in Kalman Filter resulting in extremely robust pollutant tracking. The system has been tested with successful results in the Yamuna River in New Delhi. We foresee that a system of Ro-boats working autonomously 24x7 can clean a major river in a city on about six months time, which is unmatched by alternative methods of river cleaning.
In the area of research on unmanned ground vehicles (UGV), one major problem is limited operating duration of robotics vehicles due to energy losses. There is a need for systematic analysis of locomotion and energy dynamics, which would enable an efficient design of the vehicle. For this purpose, a multifunction simulator tool is required which can read several input variables that describe the vehicle and compute detailed analysis of its energy dynamics. This research presents a generic locomotion simulator for a UGV (SimUGV). SimUGV's goal is to help vehicle designers develop efficient vehicles by optimizing design variables to minimize the energy losses for the vehicle. SimUGV has a powerful GUI interface which allows users to compare multiple test runs and visualize the data in a variety of ways. To illustrate the capabilities of the simulator, we present a case study conducted on the energy dynamics of a skid steering robotic vehicle. Two major constituent components of energy losses/consumption for a skid steering vehicle are - losses in skid steer turning, and losses in rolling. Using SimUGV, we present a detailed energy loss analysis of the vehicle's different turning modes; elastic mode steering, half-slip steering, skid turns, low radius turns, and zero radius turns. Each of the energy loss components is modeled from physics in terms of the design variables. The effect of design variables on the total energy losses/consumption is then studied using simulated data for different types of surfaces i.e. hard surfaces and muddy surfaces. Finally, we make suggestions about efficient vehicle design choices in terms of the design variables.
KEYWORDS: Receivers, Transceivers, Control systems, Data communications, Niobium, Sodium, Telecommunications, Wireless communications, Data transmission, Mining
The demand for spontaneous setup of a wireless communication system has increased in recent years for areas like battlefield, disaster relief operations etc., where a pre-deployment of network infrastructure is difficult or unavailable. A mobile ad-hoc network (MANET) is a promising solution, but poses a lot of challenges for all the design layers, specifically medium access control (MAC) layer. Recent existing works have used the concepts of multi-channel and power control in designing MAC layer protocols. SU-MAC developed by the same authors, efficiently uses the 'available' data and control bandwidth to send control information and results in increased throughput via decreasing contention on the control channel. However, SU-MAC protocol was limited for static ad-hoc network and also faced the busy-receiver node problem. We present the Extended SU-MAC (ESU-MAC) protocol which works mobile nodes. Also, we significantly improve the scheme of control information exchange in ESU-MAC to overcome the busy-receiver node problem and thus, further avoid the blockage of control channel for longer periods of time. A power control scheme is used as before to reduce interference and to effectively re-use the available bandwidth. Simulation results show that ESU-MAC protocol is promising for mobile, ad-hoc network in terms of reduced contention at the control channel and improved throughput because of channel re-use. Results show a considerable increase in throughput compared to SU-MAC which could be attributed to increased accessibility of control channel and improved utilization of data channels due to superior control information exchange scheme.
Multi-channel medium access control (MAC) protocols have been developed to overcome the contention/collision problems that arise with single channel MAC protocols in ad-hoc wireless networks. In most of the currently available schemes, a single pre-assigned control channel carries all the control packets (RTS/CTS/RES) for data communication. One of the problems identified with this method is that as the number of nodes in a system increases, the throughput drops significantly due to heavy contention on the control channel. Moreover, even if several data channels are available in the system, many of them remain underutilized due to the unavailability of the control channel. This paper presents SU-MAC, a Smart Utilization MAC protocol, that assigns the available multi-channels dynamically. Our protocol combines the control and available data channel bandwidth to send control information and thus avoids blockage of the control channel for long periods. A power control scheme is also used as well to reduce interference and to effectively re-use the available bandwidth. Simulation results show that our SU-MAC protocol is promising in terms of reduced contention at the control channel and improved throughput because of channel re-use.
In the area research on unmanned robotic vehicles, there is a need for systematic analysis of locomotion and energy dynamics, which would enable an efficient design of the vehicle. This research builds upon the earlier research by the authors and develops techniques to derive efficient design parameters for skid steering vehicle in order to achieve optimal performance by minimizing the energy losses/consumption. Two major constituent components of energy losses/consumption of the vehicle are - losses in skid steer turning, and losses in rolling. Our focus is on skid steering, we present a detailed analysis of skid steering for different turning modes; elastic mode steering, half-slip steering, skid turns, low radius turns, and zero radius turns. Each of the energy loss components is modeled from physics in terms of the design variables. The effect of design variables on the total energy losses/consumption is then studied using simulated data for different types of surfaces i.e. hard surfaces and muddy surfaces. Finally, we make suggestions about efficient vehicle design choices in terms of the design variables.
One of the major problems with any robotic vehicle is inefficient use of available power. This research explores in detail the locomotion, power dynamics and performance of a skid steered robotic vehicle and develops techniques to derive efficient design parameters of the vehicle in order to achieve optimal performance by minimizing the power losses/consumption. Three categories of design variables describe the vehicle and its dynamics; variables that describe the vehicle, variables that describe the surface on which it runs and variables that describe the vehicle’s motion. Two major constituent components of power losses/consumption of the vehicle are − losses in skid steer turning, and losses in rolling. Our focus is on skid steering, we present a detailed analysis of skid steering for different turning modes; elastic mode steering, half-slip steering, skid turns, low radius turns, and zero radius turns. Each of the power loss components is modeled from physics in terms of the design variables. The effect of design variables on the total power losses/consumption is then studied using simulated data for different types of surfaces i.e. hard surfaces and muddy surfaces. Finally, we make suggestions about efficient vehicle design choices in terms of the design variables.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.