Person Detection in Video Based on Deep Learning
Typ Master, IDP, Forschungspraxis
Betreuer Dr.-Ing. Mohammadreza Babaee
Tel.: +49 (0)89 289-28543
Sachgebiet Computer Vision
Beschreibung In intelligent visual surveillance, people are usually observed with distant from multiple cameras. Generally, face recognition techniques are used to identify the individuals. However, the shortcomings of this approach are low-resolution face image, due to large distances, unexpected view angle, and occlusion.
Today, convolutional neural networks (CNN) or deep learning algorithms play a key role in many computer vision problems such as image super resolution, image classification, and object recognition. These algorithms are mainly used to learn image representations from image content instead of hand crafted features such as SIFT, HOG, SURF, etc.
In this project, the goal is to apply deep learning for detection of people in videos. For this, we need to employ one of the state-of-the-art deep learning algorithms for segmentation. For instance, in [3], deep learning algorithms have been used to do a senmantic segmentation. See below.

Here, convolutional neural networks can efficiently semantically segment the input images in the foreground and background, where foreground are cats.
Inspiring by [3], we would like to do semantic segmentation for person detection in video. To this end, we encourage to use open-source deep learning software like caffe [2] to implement the algorithm.


[1] Erhan, Dumitru, et al. "Scalable object detection using deep neural networks." Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. IEEE, 2014.
[3] J. Long, E. Shelhamer, T. Darrell. “Fully convolutional Neural networks for semantic segmentation”. CVPR 2015.
Voraussetzung Preliminary knowledge in Machine learning and good programming skill in Matlab and C++ is highly required. For further questions, please write me an email to set an appointment in order to discuss further.
Bewerbung If you are interested in this topic, we welcome the applications via the email address above. Please set the email subject to “<Type of application> application for topic 'XYZ'”, ex. “Master’s thesis application for topic 'XYZ'”, while clearly specifying why are you interested in the topic in the text of the message. Also make sure to attach your most recent CV (if you have one) and grade report.