Training Data Extraction and Object Detection in Surveillance Scenario
Artur Wilkowski , Maciej Stefańczyk , Włodzimierz Kasprzak
AbstractPolice and various security services use video analysis for securing public space, mass events, and when investigating criminal activity. Due to a huge amount of data supplied to surveillance systems, some automatic data processing is a necessity. In one typical scenario, an operator marks an object in an image frame and searches for all occurrences of the object in other frames or even image sequences. This problem is hard in general. Algorithms supporting this scenario must reconcile several seemingly contradicting factors: training and detection speed, detection reliability, and learning from small data sets. In the system proposed here, we use a two-stage detector. The first region proposal stage is based on a Cascade Classifier while the second classification stage is based either on a Support Vector Machines (SVMs) or Convolutional Neural Networks (CNNs). The proposed configuration ensures both speed and detection reliability. In addition to this, an object tracking and background-foreground separation algorithm is used, supported by the GrabCut algorithm and a sample synthesis procedure, in order to collect rich training data for the detector. Experiments show that the system is effective, useful, and applicable to practical surveillance tasks.
|Journal series||Sensors, [SENSORS-BASEL], ISSN 1424-8220, e-ISSN 1424-3210|
|Publication size in sheets||134.45|
|Keywords in English||object detection; few shot learning; SVM; CNN; cascade classifier; video surveillance|
|ASJC Classification||; ; ;|
|Project||National Cybersecurity Platform. Project leader: Niewiadomska-Szynkiewicz Ewa,
, Phone: 3650, start date 01-09-2017, planned end date 31-08-2020, IA/NPC/2017, Implemented
|Score||= 100.0, 12-07-2020, ArticleFromJournal|
|Publication indicators||= 0; = 0; : 2016 = 1.393; : 2018 = 3.031 (2) - 2018=3.302 (5)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.