Regardless of various research endeavors, the performance of current human detection system is still a long way from what could be utilized dependably under varying realistic environment. This is expected to some extent to the inborn troubles related to the human body and nature in which it is found. The non-unbending nature of the human body offers to ascend to varieties in the stances that it can accept and when this is combined with movement a few displaying issues are exhibited. Because of some position and angle of the camera, the view and size varieties represent some technical difficulties to the models that can be implemented. It is different with other objects that normally show up in one shape, people can be dressed in any form of changing shading and surface. The location of the human object in the environment is an essential part of the appearance. For example, the environment illumination could upgrade or corrupt the appearance relying on the direction and nature of the light. Most of the challenges with complex background are mostly experienced in the open area. Occlusion is always a challenge for robustness with several human and interactivities. This might be the parts of body cover with another part of a body which create inter-object occlusion which happens when one human walk in front and another human is behind.

As a result, we propose to develop the vision-based human detection system with Artificial Intelligence method: Deep Neural Network and Internet-of-Things (IoT) technology to strengthen the robustness of the system. FAVORIOT IoT Cloud platformact as a middleware will be fully utilized to store images to prevent data loss through the internet.

[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.

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.