Article Identification for Inventory List in a Warehouse Environment
|Title||Article Identification for Inventory List in a Warehouse Environment|
|Summary||Article Identification for Inventory List in a Warehouse Environment|
|Keywords||image segmentation, object recognition, classification, computer vision|
|TimeFrame||Start: February 2014, End: June 2014|
|References|| Lowe, David G. "Local feature view clustering for 3D object recognition." Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on. Vol. 1. IEEE, 2001.
Lowe, David G. "Distinctive image features from scale-invariant keypoints." International journal of computer vision 60.2 (2004): 91-110.
Pontil, Massimiliano, and Alessandro Verri. "Support vector machines for 3D object recognition." Pattern Analysis and Machine Intelligence, IEEE Transactions on 20.6 (1998): 637-646.
Pinto, Nicolas, David D. Cox, and James J. DiCarlo. "Why is real-world visual object recognition hard?." PLoS computational biology 4.1 (2008): e27.
Ying Liu, Dengsheng Zhang, Guojun Lu, Wei-Ying Ma, A survey of content-based image retrieval with high-level semantics, Pattern Recognition, Volume 40, Issue 1, January 2007, Pages 262-282, ISSN 0031-3203
Mutch, Jim, and David G. Lowe. "Multiclass object recognition with sparse, localized features." Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on. Vol. 1. IEEE, 2006.
|Prerequisites||Image Analysis, Machine Learning, programming skill|
|Supervisor||Björn Åstrand, Saeed Gholami Shahbandi|
For the purpose of intelligent warehouse development, an important step is a better understanding of the environment. One of the elements that provide this better understanding is an inventory list of articles. Automatic construction of an inventory list in a warehouse environment requires detection, identification, quantity estimation and localization of stored articles from images. These images are stored via a camera mounted on lift-trucks operating in a real warehouse.
Research Question: How to employ environmental structure (pallets or pallet rack cell) to handle challenging image segmentation in a highly cluttered scene is one of the questions that should be answered. Fast features description for object recognition in a warehouse environment is another challenge required for handling a sequence of images.
Work package 1: image preprocessing (system setup) Work package 2: object detection (image segmentation) Work package 3: object recognition (classification) Work package 4: quantity estimation (bonus part)
Deliverable: an implementation and demonstration of a developed method for listing articles appearing in an image sequence.