Related Experiment Video
Updated: Sep 12, 2025
08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
1.6K
Vision-based volumetric estimation of localized construction and demolition waste
Ashwani Jaiswal1, Kunal Jha1, Nikhil Bugalia1
1Department of Civil Engineering, Indian Institute of Technology Madras, Chennai 600036, India.
Waste Management (New York, N.Y.)
|August 5, 2025
Summary
This study introduces a new vision-based framework for accurately estimating construction and demolition waste (CDW) volumes using consumer cameras. The automated system efficiently quantifies small, localized CDW stockpiles for improved reverse supply chain operations.
Area of Science:
- Environmental Engineering
- Computer Vision
- Supply Chain Management
Background:
- Accurate quantification of localized construction and demolition waste (CDW) is crucial for optimizing upstream reverse supply chain (RSC) operations.
- Existing methods for CDW quantification are often large-scale, semi-automated, and rely on expensive equipment, making them unsuitable for small, localized stockpiles.
- Frequent estimations of scattered CDW are needed for effective urban waste management.
Purpose of the Study:
- To develop and validate a novel vision-based framework for automated, fast, and accurate volume estimation of small-scale, localized CDW.
- To address the limitations of existing methods in quantifying scattered CDW in urban environments.
- To provide a practical tool for decision-making in upstream CDW reverse supply chain operations.
Main Methods:
- A hybrid segmentation technique combining a modified RANSAC algorithm for ground plane identification and a clustering process.
- Development of a Multi-View Classification Model (MVCM) using ResNet-50 architecture for CDW cluster recognition.
- Volume estimation of recognized CDW clusters using a Delaunay triangulation-based approach.
Main Results:
- The framework achieved a high F1 score of 0.97 for CDW identification using the MVCM on 3500 images.
- Volume estimation demonstrated high accuracy with an absolute percentage error (APE) of 8.97% compared to manual measurements.
- The end-to-end processing time was 11 minutes, highlighting the framework's efficiency for field deployment.
Conclusions:
- The proposed vision-based framework offers an automated, efficient, and accurate solution for quantifying localized CDW.
- This technology is highly practical for upstream RSC operations, enabling better management of scattered urban waste.
- The study validates the framework's effectiveness using an extensive dataset from both laboratory and field environments.
Keywords:
Construction and demolition wasteDeep learningHybrid segmentationPoint cloudQuantificationReverse supply chainMore Related Videos
Related Concept Videos
01:12Total Voids in Concrete
204
Total voids in concrete encompass gel water volume, capillary pores, and entrapped air. Gel water (retained within the cement hydration products) and physically entrapped or adsorbed water are significant for the hydration process. For complete hydration, it's estimated that the space needed for the products of a cubic centimeter of cement doubles. Capillary pores constitute the unoccupied space within the hydrated cement paste, with their size largely influenced by the water-to-cement...
204
01:23Measurement of Air Content in Concrete
270
Air content measurement in concrete is critical for ensuring structural integrity and durability of concrete structures, especially in environments prone to severe weather conditions. Accurate air content analysis optimizes concrete's resistance to freeze-thaw cycles and enhances its workability and strength. Several methods are standardized under ASTM guidelines to measure the air content in fresh concrete, each suitable for different concrete types and conditions.
The pressure method,...
The pressure method,...
270