International Conference on Computer and Knowledge Engineering

Home / 11th International Conference on Computer and Knowledge Engineering

Automatic Infrared-Based Volume and Mass Estimation System for Agricultural Products

Authors :

Seyed Muhammad Hossein Mousavi¹ S. Muhammad Hassan Mosavi²

1- Independent Scientist 2- Independent Scientist

Keywords :

Agricultural products grading, Automatic volume and mass estimation, Kinect Version 2, Depth image, Irregular and non-symmetrical shaped products, Real time calculation

Abstract :

Volume and mass estimation are two important factors in quality grading for agricultural products. Using novel automatic volume and estimation systems decreases the human error and saves significant amount of time in this process. Novel methods use color image (and some cases depth image) to estimate the volume and mass, but still there are considerable amount of error in irregular and non-symmetrical shaped products and they do not work properly in different distances from product. Proposed method uses Kinect version 2 sensor to fix this problem using produced depth images from infrared sensor. Totally 10 features out of color and depth images are extracted which volume and mass are just two of them. Also, proposed method works very well in pure darkness. Another mentionable feature is fast response in real time calculation. The final results show improvement in compare to traditional and novel methods.