Image Processing and Analysis

Purdue Engineering at its finest Learn more

Community Partners

Team Touch
Department of Speech, Language, and Hearing Sciences,
College of Health and Human Sciences, Purdue University

member

Team Sleep
Developmental Studies Laboratory,
Purdue University

Team PhenoSorg (past project)
US Department of Energy

member

Welcome To IPA

IPA is an Engineering Projects in Community Service (EPICS) working on projects that use imaging based processing and analysis for a variety of societal needs.

Read More

Projects

  • touch_XiaoXiao.jpg

    Xiao Xiao

  • touch_Xinyi_Peng.jpg

    Xinyi Peng

  • touch_Shuheng_Lin.jpg

    Shuheng Lin

Team Touch

Early social interaction events such as 'touch' may have important influence on infants' speech perception. It is important for researchers to study the 'touch' interaction between caregivers and infants so they can determine how touch impacts infant language development. This project aims to automate detection of touch between the caregivers and infants to facilitate processing the correlation between the touch frequency and infant learning. It will utilize the information captured by an RGB camera and depth sensor provided by Microsoft Kinect. Our team will design a system that uses a RGB camera and a depth sensor to acquire 3D information of the model/wireframe of the caretaker. The system will then process the RGB data and depth information to reconstruct a 3D mesh of the caretaker and the infant. Afterwards, an algorithm will be used to detect collision between the 3D meshes, which will constitute a 'touch'. The frequency of touches will be recorded over a given period of time and be made available for researchers.

  • sleep_Emily_Bartusiak.jpg

    Emily Bartusiak

  • sleep_Kyla_Hayes.jpg

    Kyla Hayes

  • sleep_Michael_Huskey.jpg

    Michael Huskey

Team Sleep

The sleep team project involves analyzing videos of toddlers sleeping to detect sleep problems. We are designing a software tool to reduce the time­required for analysis for Human Video Somnography. The end­user of our software will be sleep researchers who want to investigate links between sleep cycle and the potential of numerous disorders especially autism. The deliverable for our project is to produce image­processing algorithms to detect Periods of Interest containing anomalies during sleep based on the intensity and frequency of movement and to provide a user­friendly interface for doctors to analyze the sleep problems.

Team PhenoSorg (past project)

Modern farming techniques now include collecting information from both ground based and airborne sensors (e.g. drones). This team will work closely with a recently funded research project sponsored by the US Department of Energy. In this project we are interested in using imaging sensors (cameras) and 3D sensors to acquire data throughout the growing period on plant characteristics and develop models to predict the ultimate biomass yield of a crop. The particular crop we are using for our study is sorghum. We are collecting these images from drones and ground based sensors. The images are analyzed to estimate phenotypic properties of the sorghum plants. This includes plant height, number and area of leaves, chemistry related properties, and other traits. The team will work on two tasks: analyzing the sensor data and designing the ground based sensor platform.

Contact Us

Purdue UniversityNeil Armstrong Hall of Engineering Room 1200 701 West Stadium AvenueWest Lafayette, IN 47907-2045


Phone: 765-494-3750