Human detection and tracking system are one of the most fundamental tasks in computer vision field where motion detection and tracking are coupled to locate human through the video captured by an observer (installed camera). Optical flow algorithm is one of the methods that used to analyze the path of pixels and reflects and the apparent changes of the targeted moving object between previous and current locations. It is frequently applied in human detection and tracking system since it is easier to be applied to input sources and variations-effective. However, detecting humans in sequences of frames or even in a real-time video is still very challenging due to their appearance variations and different poses adoptions.

Security is becoming the main concern of society in urban cities since the scarcity of jobs raise, which indicates that property of residents is being threatened by thefts and destruction. Traditional surveillance systems need human operators to differentiate all activities and behaviors of objects for forensic investigation purpose and require significant judgment and decision for an event happening, there is a probability of mistake due to a long period of passive watching which results in negligence. Besides, a huge amount of data received is impossible to be handled and extracted due to time-consuming and high expenses. Therefore, this project is proposed to develop a computer vision system for real-time human detection and tracking using optical flow algorithm.

Human will be identified and tracked with classifier with the features extracted by the human descriptor. Human behaviors will be analyzed and interpreted based on video frames obtained from the observer (camera). Raspberry Pi 3 board is selected to develop and implement detection and tracking and FAVORIOT middleware will be used as a communication media that allows all data from IoT end device to be uploaded and used as administration references.

[Note: This project is being done by UPM, our FAVORIOT’s University’s collaborator]

You can check out the whole LIST of IOT PROJECTS by our University Collaborators.

Nowadays, there has been a high exposure to ethanol that can give side effect to the human. The cost-effective on monitoring the ethanol concentration with high selectivity based on optical based is developed. The ethanol sensor is developed using uncladded plastic optical fiber (UCPOF) and being coated with nanomaterials. The system is using the photodiode to interrogate the signal since it has the high sensitivity on wavelengths changes. The light source that travels along the ethanol sensor will be converted into the corresponding current. Then, the trans-impedance amplifier will convert the current into a voltage and received by Arduino UNO microcontroller. The sensor is having the ability to monitoring the remote sensor since it developed in small size. The advancement of this system, the project can monitor the ethanol in the long distance with the aid of Internet of Things (IoT) by using FAVORIOT IoT Cloud. The power of light intensity will be recorded in the Cloud. The collection of data in this system can be viewed and monitored in FAVORIOT website. The recorded data can be used to taking the fast action when will have the high exposure to ethanol.

[Note: This project is being done by UPM, our FAVORIOT’s University’s collaborator]

You can check out the whole LIST of IOT PROJECTS by our University Collaborators.

Gas leakage detection at refilling station and storage area was either manual or local detection and monitoring only. should any leakage occur at odd hours where no personnel are around, then it may cause a hazard to people. This project will solve the issue of LPG leakage using relevant sensors for detection and provide IoT for real-time notification using the Favoriot platform.

[Note: This project is being developed by UTeM. Article was written by Mazran Esro]