Object Instance Segmentation Using Boundary Maps for Occluded Scenes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object identification methods in images struggle with fragmented parts, particularly in complex environments with occlusions, varying body proportions, and clothing, leading to challenges in creating meaningful object and instance segmentations.
Innovation Solution
An apparatus and method using a neural network to predict boundary maps and a post-processing engine to combine encoded maps, dynamically adapting to input characteristics, effectively clustering object fragments and providing accurate instance segmentations in complex scenes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If edge-based segmentation detection and computer vision methods are used to identify objects in images, then object identification capability is improved, but performance deteriorates when objects are fragmented or occluded in complex environments
Solution Approach 1:
The patent applies segmentation by dividing the object identification task into multiple stages: initial object detection, fragmentation analysis, and iterative reconstruction. The system segments fragmented objects into detectable parts and progressively reconstructs complete object instances, resolving the contradiction between maintaining identification accuracy and handling fragmented/occluded objects in complex environments.
2Productivity
If traditional object identification methods are applied to complex scenes with occlusions and varying body proportions, then processing speed is maintained, but segmentation quality and meaningful object separation deteriorate
Solution Approach 1:
The patent implements preliminary action by performing initial object detection and fragmentation analysis before final instance segmentation. The system pre-processes images to identify potential object regions and fragmentation patterns, then uses this preliminary information to guide the iterative reconstruction process, thereby maintaining processing speed while improving segmentation quality in complex scenes.
3Adaptability or versatility
If dynamic adaptation to input characteristics is implemented through neural networks and post-processing engines, then adaptability to varying conditions is improved, but system complexity increases
Solution Approach 1:
The patent applies dynamics by implementing a neural network-based system that dynamically adapts to varying input characteristics such as different object types, occlusion levels, and image conditions. The post-processing engine dynamically adjusts processing parameters and reconstruction strategies based on detected fragmentation patterns, enabling high adaptability while managing system complexity through automated decision-making algorithms.
Data Source
AI summary
An apparatus is provided. The apparatus includes a communications interface to receive raw data from an external source. The raw data includes a representation of a first object and a second object. The apparatus further includes a memory storage unit to store the raw data. In addition, the apparatus includes a neural network engine to receive the raw data. The neural network engine is to generate a segmentation map and a boundary map. The apparatus also includes a post-processing engine to identify the first object and the second object based on the segmentation map and the boundary map.