• Ms. Vrushali Rajaram Patil
• Rahul S. Kumbhar
• Mahesh S. Bhosale
• Virendra C. Patil

Terrorism & global security is one of the major issues worlds facing today. We have seen in recent terrorist attacks involving some suspicious bags which are left unattended at railway stations, shopping malls, airports etc. The most challenging task in video surveillance system is to detect such kind of suspicious bags. So, for that purpose it is necessary to have an efficient threat detection system which can detect & recognize strongly dangerous situations and which gives alert to the authorities in order to take appropriate action. Our approach involves detection of abandoned baggage which is left unattended in public areas. Many methods were employed for detection of unattended objects but in this paper our focus is on the detection of abandoned objects in video surveillance system. This procedure of detection involves two stages. In first stage we are simply going to obtain foreground segments with the help of background subtraction and mean shift algorithm. In addition, with this the background subtraction is done in Hue Saturation Value color space model in order to avoid effects of illumination changes and shadows. Once foreground blobs are detected classification of foreground blobs is done in second stage based on the shape and size of binary blobs and accordingly the status of baggage is defined in order to take appropriate action. Videos are recorded at sampling rate of 25fps, at a resolution of 720x576 pixels. Few videos are used to train the algorithm. The complexity of the problem arises from obstructions present in scene, lightening conditions & shadows. Our system is able to successfully overcome these difficulties to obtain impressive results. We have used few videos for our project having different objects. Experiments were carried out in a public indoor environment

Object Detection, image processing,

"Abandoned Object Detection in Public Places", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 8, page no.c116-c125, August-2025, Available :http://www.jetir.org/papers/JETIR2508218.pdf

"Abandoned Object Detection in Public Places", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 8, page no. ppc116-c125, August-2025, Available at : http://www.jetir.org/papers/JETIR2508218.pdf