Multi-Frame Composite Imaging for Low-Light Moving Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object detection techniques in low lighting conditions, such as nighttime, suffer from poor resolution and contrast in infrared image data, leading to missed detections of moving objects due to reduced training data diversity and accuracy issues with neural networks.
Innovation Solution
Encoding a multi-channel image based on a plurality of grayscale images captured by a video camera, using a neural network to detect moving objects by leveraging artifacts like motion blur and noise, which are enhanced through a composite image generated from multiple frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If infrared image sensors are used to capture video data in low lighting conditions, then the system can operate at nighttime, but the resolution and contrast of the captured images deteriorate
Solution Approach 1:
The patent combines multiple grayscale images captured at different time points into a single composite grayscale image. By merging temporal information from multiple frames, the system enhances the effective signal-to-noise ratio and improves both resolution and contrast of moving objects in low lighting conditions without requiring additional hardware sensors.
2Extent of automation
If known object detection techniques are applied to low-resolution infrared images, then the system can detect objects, but detection accuracy deteriorates due to poor image quality
Solution Approach 1:
The patent performs preliminary image enhancement by generating a composite grayscale image from multiple frames before applying object detection. This preprocessing step improves the quality of input data for the detection algorithm, enabling more accurate detection of moving objects in low lighting conditions through enhanced contrast and resolution.
3Measurement precision
If multiple video frames are processed to improve detection accuracy, then object detection performance improves, but computational load increases
Solution Approach 1:
The patent extracts only the essential temporal information needed for improvement by combining multiple frames into a single composite image that highlights moving objects. This extraction approach achieves detection accuracy improvement while avoiding the excessive computational burden of processing and analyzing each individual frame separately.
Data Source
AI summary
A non-transitory, processor-readable medium stores instructions that, when executed by a processor, cause the processor to receive a video stream including a plurality of video frames that depicts an object in motion. From the plurality of video frames, the instructions cause the processor to select a first video frame, a second video frame, and a third video frame. Based on the first video frame, a first channel of a pixel included in an image is encoded, to define a first encoded channel. The second video frame and the third video frame are used to encode, respectively, a second channel of the pixel and a third channel of the pixel, to define, respectively, a second encoded channel and a third encoded channel. A neural network is used to detect the object in motion based on the first encoded channel, the second encoded channel, and the third encoded channel.