Waste management is an essential societal issue, and the classical and manual waste auditing methods are hazardous and time-consuming. In this paper, we introduce a novel method for waste detection and classification to address the challenges of waste management. The method uses a collection of deep neural networks to allow for accurate waste detection, classification, and waste size quantification. The trained neural network model is integrated into a mobile-based application for trash geotagging based on images captured by users on their smartphones. The tagged images are then connected to the cleaners’ database, and the nearest cleaners are notified of the waste. The experimental results using publicly available datasets show the effectiveness of the proposed method in terms of detection and classification accuracy. The proposed method achieved an accuracy of at least 90%, which surpasses that reported by other state-of-the-art methods on the same datasets.

Farmers are facing the VUCA environment (volatile, uncertain, complex and ambiguous) and data indicating the contribution of farming to India's GDP has come down from 52% to 18% between 1951 and 2018, which is alarming. At this juncture, developing countries like India, where over 70% of the rural people depend upon the agriculture fields, adoption of disruptive technology (creative destruction) becomes the need of the hour, to enhance the crop yield and quality. Weeds are one of the major issues which severely affect the crop output. Unmanned Aerial Vehicle (UAV) or drone is recommended, to address the problem. Globally, the market for agriculture drones to move from $1.3 billion to $ 6.52 billion by 2026. Globally agriculture is the second largest industry after construction in terms of drone adoption. But Indian farmers have difficulty in adopting (or) procuring UAV's, as the size of their farm is small, income is very less. Other problems associated with the adoption of UAV include knowledge transfer and training to farmers, service support and maintenance cost. DaaS (Drone as a service) model is proposed, for rural areas. This paper aims to focus on weed management by providing a safer and cost-effective solution. By integrating technologies like visible light (VIS), near-infrared (NIR) light on an Unmanned Ariel Vehicle along with a precise sprayer and a weed detection system backed up by a lithium-ion battery (for longer flight duration), can help the process of spraying weedicide efficiently. The accuracy of the tested model is 92.6% for far away detection module and 95.4 for close range detection. UAV's with sprayer protects the farmer and consumers from odour and side effects.