Computer vision techniques for construction safety and health monitoring

A vision-based motion capture and recognition framework for behavior-based safety management

Construction worker detection in video frames for initializing vision trackers

Application of machine learning to construction injury prediction

Construction performance monitoring via still images, time-lapse photos, and video streams

Tracking multiple workers on construction sites using video cameras

There has been a rapid increase in dietary ailments during the last few decades, caused by unhealthy food routine. Mobile-based dietary assessment systems that can record real-time images of the meal and analyze it for nutritional content can be very handy and improve the dietary habits and, therefore, result in a healthy life. This paper proposes a novel system to automatically estimate food attributes such as ingredients and nutritional value by classifying the input image of food. Our method employs different deep learning models for accurate food identification. In addition to image analysis, attributes and ingredients are estimated by extracting semantically related words from a huge corpus of text, collected over the Internet. We performed experiments with a dataset comprising 100 classes, averaging 1000 images for each class to acquire top 1 classification rate of up to 85%. An extension of a benchmark dataset Food-101 is also created to include sub-continental foods. Results show that our proposed system is equally efficient on the basic Food-101 dataset and its extension for sub-continental foods. The proposed system is implemented as a mobile app that has its application in the healthcare sector.

A Framework to Estimate the Nutritional Value of Food in Real Time Using Deep Learning Techniques

Regression testing is a mandatory activity of software development life cycle, which is performed to ensure that modifications have not caused any adverse effects on the system’s functionality. With every change in software in the maintenance phase, the size of regression test suite grows as new test cases are written to validate changes. The bigger size of regression test suite makes the testing expensive and time-consuming. Optimization of regression test suite is a possible solution to cope with this problem. Various techniques of optimization have been proposed; however, there is no perfect solution for the problem and therefore, requires better solutions to improve the optimization process. This paper presents a novel technique named as hybrid-adaptive neuro-fuzzy inference system tuned with genetic algorithm and particle swarm optimization algorithm that is used to optimize the regression test suites. Evaluation of the proposed approach is performed on benchmark test suites including “previous date problem” and “Siemens print token.” Experimental results are compared with existing state-of-the-art techniques, and results show that the proposed approach is more effective for the reduction in a regression test suites with higher requirement coverage. The size of regression test suites can be reduced up to 48% using the proposed approach without reducing the fault detection rate.

https://link.springer.com/content/pdf/10.1007/s00521-018-3560-8.pdf

A hybrid-adaptive neuro-fuzzy inference system for multi-objective regression test suites optimization

Time-of-Flight (TOF) sensors provide range information at each pixel in addition to intensity information. They are becoming more widely available and more affordable. This paper examines the utility of dense TOF range data for image segmentation and tracking. Energy based formulations for image segmentation are used, which consist of a data term and a smoothness term. The paper proposes novel methods to incorporate range information, obtained from the TOF sensor, into the data and the smoothness term of the energy. Graph cut is used to minimize the energy.

Visual tracking and segmentation using Time-of-Flight sensor

We propose a nonlinear covariance region descriptor for target tracking. The target object appearance and spatial information is represented using a covariance matrix in a target derived Hilbert space using kernel principal component analysis. A similarity measure is derived, which computes the similarity of a candidate image region to the learned covariance matrix. A variational technique is provided to maximize the similarity measure, which iteratively finds the best matched object region. Tracking performance is demonstrated on a variety of sequences containing noise, occlusions, illumination changes, background clutter, etc.

Omar Arif

Papers

Tracking multiple workers on construction sites using video cameras

A Framework to Estimate the Nutritional Value of Food in Real Time Using Deep Learning Techniques

A hybrid-adaptive neuro-fuzzy inference system for multi-objective regression test suites optimization

Visual tracking and segmentation using Time-of-Flight sensor

Kernel covariance image region description for object tracking