Object Detection Using Stochastic Optimization on Probability Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional object detection methods in high-definition images are computationally challenging and inefficient, leading to reduced accuracy when images are resized for faster processing, necessitating an intelligent system for enhanced accuracy and efficiency.
Innovation Solution
An electronic device employing stochastic optimization to determine probability map information using a pre-trained neural network model, selecting sub-images with higher probability values for object detection, thereby reducing processing complexity without resizing the original image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the image size is reduced to fasten object detection tasks, then processing speed is improved, but detection accuracy deteriorates
Solution Approach 1:
The patent segments the image processing task into two phases: first, a coarse detection phase on the full-resolution image to identify candidate regions; second, a refined detection phase focusing only on those candidate regions. This segmentation allows the system to maintain high accuracy by processing only relevant portions at full resolution while achieving improved speed through selective processing.
Solution Approach 2:
The patent applies local quality by processing different regions of the image with different levels of detail. High-resolution processing is applied only to candidate regions identified as containing objects, while other regions receive minimal or no processing. This ensures detection accuracy is maintained for critical areas while reducing overall computational burden.
2Measurement precision
If the full-resolution image is processed for accurate object detection, then detection accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent extracts and processes only the essential information needed for accurate detection. By using a two-stage approach where the first stage identifies candidate regions and the second stage processes only those regions, the system extracts the minimum necessary portion of the full-resolution image for detailed processing, thereby reducing computational complexity while maintaining accuracy.
Solution Approach 2:
The patent applies partial action by processing only a subset of the image data at full resolution - specifically, only the candidate regions identified in the first stage. This partial processing approach maintains detection accuracy for objects while avoiding the excessive computational cost of processing the entire high-resolution image.
Data Source
AI summary
An electronic device includes circuitry that determines probability map information for a first image, based on application of a neural network model on the first image. The neural network model is trained to detect one or more objects based on a plurality of images associated with the one or more objects. The probability map information indicates a probability value for each pixel in the first image. A region corresponding to the one or more objects is detected in the first image based on the probability map information. A first set of sub-images is determined from the detected region, based on application of a stochastic optimization function on the probability map information. The one or more objects are detected from a second set of sub-images of the first set of sub-images, based on application of the neural network model on the second set of sub-images.