Build a cctv processing script to output scenes with humans

I've done many opencv projects like this here over the past few years. If the people are >100 pixels tall, and the opencv people-detectors available (HOG,cascade) can detect them (standing, not blurry, ok lighting), this should be no problem. I can't guarantee faster than real-time until I can test with your hardware. Gpu may be an option to speed things up if you have it, and have opencv built with right options for gpu.

Hi, I have already developed pythin script which can identify human on road, for your application, i will train faster R CNN deep architecture to detect human in CCTV Video. you can see my past work (similar to your requirement) in profile section. Looking forward to work with you. Thanks

I'm interested in this project. I am not sure that I would just go with opencv, although we can start with that. I would actually use one of the already trained pedestrian detector models (there is a couple of proven ones on tensorflow), but possibly use opencv's tracking if you're actually trying to track the objects you're detecting. When you say faster than real time, can you explain what that's about, e.g. do you have a certain frame resolution and fps in mind and if so what is the reason for it (in case we can achieve the same function at a lower rate, or downsampling). You still have a few days before the bid end date. So, if you are willing to share a sample, I can play around with it and see if I can give you a proof of concept. Thanks, let me know if interested.

First of all, I think you will need gpu and large amount of ram if you want to run the script fast on that big data. I have worked on object detection , face detection as well as recognition. I have good practice in opencv, tenserflow, python, cuda , deeplearning and all those other things required for your project. I am a developer as well as data science freelancer since 2 years. Contact me if you are interested. pay me after you are satisfied . I am available 9 hrs per day for your work. You can explain your requirements or can send it to me.

hello sir, I am a student and new on this website but I have been working on machine learning and image processing for past 1 year a similar type of project I had before joining this website which was for counting the number of people currently in the room from a realtime feed using a opencv libraries. I would assure that I will complete the job by hook or crook and will be providing you with a interactive GUI along with this so you can also try some of the videos you have to test the system. I may have said that I will complete it in 3 days but I would mostly Complete the project before it as I already have a prototype for this ready. I just had one question that what kinda output do you need like you want a bunch of jpg images in a folder which contain people or a video which contains people . Well both can be done.

I have been working in these field as I also work in Cisco thingqbator lab at IIT BHU that why I think I am the best person for you