Search Results - physical+sciences+%26+engineering+%3e+infrastructure+%26+transportation

12 Results Sort By:

2026-062 - Synthetic Crack Generation for Infrastructure Inspection AI Models

Background Accurate detection of cracks in concrete and pavement infrastructure is critical for maintaining safety and durability, yet traditional manual inspections are labor-intensive and subjective. Deep learning models offer promise but are hindered by the scarcity of large, diverse, and well-annotated datasets. Existing datasets are limited in...

Non-Destructive Monitoring of Membrane Compaction

Market Opportunity Water treatment membranes are essential for processes such as seawater desalination, wastewater treatment, and potable water reuse. Current methods to assess membrane compaction-- like scanning electron microscopy (SEM)—only capture static measurements before and after stress, lacking real-timeinsights. This creates a critical...

2016-249 - Improved High-Resolution Sensing Technology for Autonomous Vehicles

Market Opportunity Demand for autonomous vehicles is expected to reach 29 million units by 2035. High-resolution detection and ranging technologies, such as LiDAR, are used in autonomous vehicles for remote sensing. Using LiDAR to create, steer, and detect high-resolution optical beams in free-space allows capturing real time 3D data for a diverse...

2019-067 - Adaptive Control of Multi-Zone HVAC System

Building systems HVAC controls Heating and cooling Abstract USC researchers have designed a control system using a distributed approach with zones, combining adaptation and learning. The building is divided into different thermal zones, where each zone has its own controller. The main difference from current state of the art solutions is that the...

2022-182 - Automatic Vehicle Following System under Safety, Comfort, Road Geometry Constraints and Sensor Uncertainty

Advanced driver assistance systems Autonomous vehicles Abstract USC researchers have developed a practical solution to address the challenges of autonomous vehicle navigation. Their proposed methodology incorporates geo-referenced maps that identify road geometries and detect objects in the vehicle's path. It considers the impact of sensor noise...

14-007 - Increased Flow Reverse Osmosis Membranes Containing Nano Objects

Market Opportunity Separation processes are important for the chemical, pharmaceutical, petroleum, electronics, automotive, and aerospace industries, and efficient water reclamation technologies are increasingly needed due to drought, and water shortages. Current separation processes are often energy intensive and incur high operating costs. Membrane...

2024-171 - Ultra-High Durability Cement Mortar Plug for Oil and Gas Wells

Abstract Millions of abandoned oil and gas wells leak methane and harmful chemicals, threatening groundwater, fueling climate change, and creating regulatory headaches. Traditional cement plugs crack, shrink, and fail. Alternatives like bismuth and resin are pricey, tricky, and unreliable. Benefit A breakthrough cement composite plug engineered for...

2020-146 - Cooling, Smog-Filtering Building Facade Panel

Market Opportunity Despite cleaner fuels and more efficient engines, a global rise in urban air pollution presents a significant health crisis. This escalating issue calls for innovative architectural solutions that can mitigate air pollution, thus creating a substantial opportunity for architects to develop structures that contribute to public health...

09-336 - Object Tracking by Hierarchical Association of Detection Responses

Security surveillance Driving assistance systems Smart home Abstract USC researchers introduce a three-level hierarchical association approach to track multiple objects in crowded environments using a single camera. At the low level, reliable tracklets are generated by linking detection responses with conservative affinity constraints. These tracklets...

11-668 - Adaptive Vision-Based Crack Detection with Depth Perception

Civil infrastructure inspection Building inspection Abstract USC researchers introduce a vision-based crack detection methodology that processes 2D digital images by analyzing the scene's geometry. The methodology incorporates feature extraction and classification techniques to distinguish cracks from non-crack patterns. Experimental tests have...

1 2