Parts-per-Object Count in Agricultural Images: Solving Phenotyping Problems via a Single Deep Neural Network

Solving many phenotyping problems involves not only automatic detection of objects in an image, but also counting the number of parts per object. We propose a solution in the form of a single deep network, tested for three agricultural datasets pertaining to bananas-per-bunch, spikelets-per-wheat-spike, and berries-per-grape-cluster. The suggested network incorporates object detection, object resizing, and part counting as modules in a single deep network, with several variants tested. The detection module is based on a Retina-Net architecture, whereas for the counting modules, two different architectures are examined: the first based on direct regression of the predicted count, and the other on explicit parts detection and counting. The results are promising, with the mean relative deviation between estimated and visible part count in the range of 9.2% to 11.5%. Further inference of count-based yield related statistics is considered. For banana bunches, the actual banana count (including occluded bananas) is inferred from the count of visible bananas. For spikelets-per-wheat-spike, robust estimation methods are employed to get the average spikelet count across the field, which is an effective yield estimator.

Density and Time based Traffic Control System using Video Processing

Traffic is the serious issue which each nation faces due to the expansion in number of vehicles. One of the strategies to beat the traffic issue is to build up a smart traffic control framework which depends on computing the traffic density and about utilizing constant video and picture preparing procedures. The topic is to control the traffic by deciding the traffic density on each roadside and control the traffic signal smartly by utilizing the density data. In this paper, an automated system based on processing of real time videos is proposed for detection of vehicles and recording count of them. The System will consist of various stages which includes Object Car Detection and Signal variation based on density. Captured video will be converted into frames and which will be pre-processed for object detection using Haar-Cascade than detected object count will be used to obtain the density and manipulate the signal accordingly. The density count algorithm works by contrasting the ongoing edge of live video by the reference picture and via looking through vehicles just in the district of intrigue (for example street region). The figured vehicle thickness can be contrasted and other course of the traffic so as to perform control of the traffic flags in more smart and proficient manner.

Estimage: A mobile application in agriculture for image to object count estimation

A major problem in the agricultural field is accurately estimating the yield of produce. Typically, farmers must wait to measure their crops after harvest using manual mechanical equipment. There is value in having better methods of yield estimation based on data that can be captured with inexpensive technology in the field, such as a smartphone. We develop a smartphone application for the Android platform with access to a cloud-based machine learning (ML) service that can estimate the amount of crop on a bush or tree from an image. The development of an image-to-object-count estimation system called Estimage is presented. The Estimage system consists of an Android client application for user interaction, a PHP server application for request handling, an Octave program for image normalization, and an open-source ML software package called ilastik that applies a predictive model to an image. The functionality of the mobile client application is tested and the system satisfies all of the functional requirements and most of the non-functional requirements. The system is tested on the images of coins on a table, logs stacked in a pile, and blueberries on the bush. We show that the system is capable of accurately estimating the count of objects in the images that have objects of the same (size, colour, and shape) as that used to train the model. The system is good at distinguishing object pixels from the image background pixels provided the background is consistent with that used to train the model.