Identifying highly vulnerable mosquito breeding sites using machine learning and drone based aerial survey

This study deals with Drone based Aerial Survey in analyzing and identification of highly vulnerable mosquito breeding sites at Buckingham canal Chepauk, Chennai. It is small section of Buckingham canal studied using the drone for capturing the images and furtherly images were processed for identifying the sites prone to breeding of mosquitos. Approach used here of capturing images and classifying the vulnerable sites, using a machine learning approach in for extracting features using the algorithm and later generating a Support Vector Machine to train and classify the images. Tensorflow object detection algorithm was used to detect the object and also generate the probability level. Tensorflow based supervised classification involves stacking multiple layers of neural network for a classification. Methods like back propagation invoked in the neural networks ensures the classification accuracy are increased. In this algorithm Single shot multi box detector (SSD) has been used which provides fast detection. Single shot multi box detector (SSD) method is based on a feed-forward convolutional network, followed by a non-maximum suppression step to produce final detections. The accuracy constraint of 70% was kept for qualifying as a potential site to negate ambiguities arising due to processing errors

Artificial neural network · Computer vision · Convolutional neural network · Detector · Drone · Identification (biology · Machine learning · Object detection · Pattern recognition (psychology · Single shot · Support vector machine · Computer Science · Digital Imaging for Blood Diseases · Remote-Sensing Image Classification · Smart Agriculture and AI · Artificial Intelligence

• Distinctive Image Features from Scale-Invariant Keypoints

  Open Access•David Lowe, David G Lowe•International Journal of Computer…•2004

  Add to list