Low Light / IR Face Detection

Interested to know more? Do you have a potential use case? Fill the below form to contact us.






Congratulations. Your message has been sent successfully.
Error, please retry. Your message has not been sent.

Instructions
Input - Click on the “+” button in the video player and upload a decent resolution video with less than 40mb. Video or image with face closeups taken from an IR camera is recommended for better performance.
Output - Provides an image or a video with the people's faces localized even in a low light condition provided the face is closer to the IR camera. Can detect multiple faces present in the image or video with face location (XY coordinates) in a JSON format.
Note: Upload the appropriate video for optimal performance. Uploading any video that doesn't relate to the model might provide you unexpected results.

The ability to understand and interpret facial structures is essential to many image analysis requirements. A human face is a biometric element that can be used in an automated computer-based security system to identify or authenticate. In the example of low light face detect, the model provides the detection box around each face of human beings in illuminations variations such as indoor and outdoor lighting conditions and low lighting.

The low light or night vision conditions are challenging for facial detection systems, but this model exceeds the limitations of face detection in such conditions and helps to identify the person as well. Taking an example of a vehicle driver monitored by an IR vision camera can actually help detect the distractions to drowsiness. This can also help solve a few critical challenges in crime investigations.

Use Cases

Face Recognition, Surveillance and Security System, Identification of a Person in Night Conditions etc.,

API Request and Response

TensorGo Platform provides you with a one stop solution to customize the our API offerings as per your use case by mixing and matching the existing APIs or requesting for a new custom model. This accelerates the development of use cases with minimal or no code towards deep learning applications.
The endpoint for API is:
[URL]
Request:
post/
[URL]
	body:{
		id:”Some Unique  ID”
		app:”Name of the app”
		file:”Attached File”
             }
Example:
post/
	[URL]
	body:{
		id:xsk231ds168wd
		app:faceDetectIR
		file:”Attached File”
             }

Response:
	{ msg:Uploaded }

Download the Uploaded video:
get/
	[URL]
	body:{
		id:xsk231ds168wd
		app:faceDetectIR
             }