You've landed at the right place. oDesk is now Upwork. Learn about the new platform.

Opencv Jobs

20 were found based on your criteria

show all
show all
only
only
only
show all
only
only
only
only
only
show all
only
only
only
Hourly - Est. Time: 1 to 3 months, 10-30 hrs/week - Posted
Looking for a scientific programmer with solid background in image processing. Must be fluent in MATLAB, OpenCV + C++, or OpenCV + Python, and comfortable implementing mathematical algorithms. Experience in image registration and feature-based classification is a big plus. This is a part-time (15-25 hours/week) position for at least one month, but it may turn into an ongoing engagement for the right candidate. Smart Systems Consulting in Boston, USA, has a contract with a life sciences company that is developing a revolutionary image-analysis platform. Your role will be to implement image enhancement and analysis algorithms, and build data-handling software utilities to support a small team of physicists and computer vision experts.
Fixed-Price - Est. Budget: $ 50 Posted
I NEED THIS TO BE DONE BY 12 o'clock IST I have a already working modal in Visual C++ with OpenCV libraries and it is developed for examination surveillance and the current functionalities of this modal is as below:- -> Motion detection of the person and capturing it in a image formats. • Face movement detection's • Body parts Movement detection's • When New object came in frame it detects I already have working modal with above functionality in two scenarios, one is it will detect all above, like as in a live streaming(While camera in front of the person and save the video also for future) and second is we can provide a video file as a source from which it can detect above things. WHAT I WANT IS THE VIDEO FILE IS SAVING IN .avi FORMAT, I WANT TO STORE THE VIDEO IN .webm FORMAT INSTEAD OF .avi Here I have attached the code of working modal, REVIEW IT AND GIVE YOUR TIME ESTIMATION I am using OpenCV libraries with VC++ for this, so please be careful at this points, I...
Skills: OpenCV
Hourly - Est. Time: 1 to 3 months, Less than 10 hrs/week - Posted
I need help with face profiling through image in an iOS application. I am trying to detect left ear, nose and mouth in a given image. So far I tried OpenCV, I found voila's haar classifiers but this haar classifier does not detect left ear. I need to perform this detection without going to server/online. Is OpenCV good choice for this? Any sample codes you can share to achieve this functionality would be great. What can be other choices to achieve this functionality? I can hire you urgently if you can assist with this problem. And this could be a long term job if you have right skills to remove my current roadblock.
Hourly - Est. Time: Less than 1 week, 10-30 hrs/week - Posted
Hello, developers I have an iOS app that provides image recognition/processing function. The app also has Social chatting function too. The app has several bugs to be fixed immediately. Some of them are related to the image post processing. The others are for the SNS chatting functions. Once the few bugs are fixed, you should help me upload to Apple Appstore. I'll share detail of the work once you show me the possibility for the job. Thanks.
Fixed-Price - Est. Budget: $ 1,000 Posted
We are looking for a software developer with knowledge in Video, OpenCV, Computer Vision and Image Processing. Expertise counting people and doing face recognition or gender detection is a plus. The candidate will need to have knowledge on the different ways available for counting people using video cameras. Special knowledge will be needed when counting many people crossing an area at the same time (from 4 to 8 meters wide) which can stand for thousands of people in a matter of minutes. Knowledge in Products and API Tools already developed for Video Analysis Technology also will be assessed. Further project details will be provided to candidates in the short list. Please type "I am an OpenCV expert" at thecovers beginning to apply.
Fixed-Price - Est. Budget: $ 30 Posted
I have few (tens) of IP cameras. Each of them have http streaming accessible via address like "http://192.168.1.100:8080/video", and this is mJPEG stream. I have one main server, for example "http://192.168.1.1" I need: 1) All of cameras streams, accessible into one webpage, with some features (like motion detection, etc) - http://192.168.1.1/index.html; 2) Default quality of mJPEG video should be 30% (there are simple API to change it, like curl request "http://192.168.1.100:8080/quality=30"), but when motion is detected, event should run "http://192.168.1.100:8080/quality=100"; 3) All streams of webcameras should be saved into separate video files (named by date or something else), using quality settings set with previous option (30 by default, 100 for movements); 4) With the adjustable option, frame with camera could be higlighted when movement detected on this camera 5) This system should be easy. One daemon (python script) to collect all streams from cameras, to...
Fixed-Price - Est. Budget: $ 400 Posted
We are in need of a developer who is fluent with Open CV. The job would include facial tracking, and tracking of individual facial features such as eye, lip, cheek, and nose shapes. You will need to know OpenCV, basic knowledge of Unity3D, and Android/iOS requirements for optimization purposes. We are looking for someone who will mesh well with the team and meet deadlines.
Fixed-Price - Est. Budget: $ 150 Posted
Develop a REST service for detecting human faces on photos. There is only one endpoint: - GET /faces/<id>?url=<escaped image url> - The service just fetches the image, detect faces, then discard, so no file storage or DB is needed. - ID is just for caching in the future, so that's not really used - Returns JSON list of face rectangles as in [{'x': 0.1, 'y': 0.2, 'width': 0.25, 'height': 0.3}] - These are all fractions of the image's dimensions. For example, if the image is 100 pixels wide and X is at pixel 25, response should be 0.25 You must proof your code works by building up a test case of 200+ images, some with 1 face, some none, some many, some half, some clear, some obscure. Unit tests must proof performance and accuracy. Technologies to base on: - Java - Spring - Gradle General requirements: - Unit tested - Clean object-oriented code - Fast (<100ms/operation on 100k+ data set on regular hardware) I have other projects for you if you can do this...