working on an AI chatbox that help teach programming to newbies by providing templates, solutions, guidance and periodical evaluation of each students
Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness
Kelowna, British Columbia
We proposed a novel object detection framework using image fusion and convolutional neural networks (CNNs) for the military scenario.
- 0 Followers
Object Detection is critical for automatic military operations. However, the performance of current object detection algorithms is deficient in terms of the requirements in military scenarios. This is mainly because the object presence is hard to detect due to the indistinguishable appearance and dramatic changes of object's size which is determined by the distance to the detection sensors. Recent advances in deep learning have achieved promising results in many challenging tasks. The state-of-the-art in object detection is represented by convolutional neural networks (CNNs), such as the fast R-CNN algorithm. These CNN-based methods improve the detection performance significantly on several public generic object detection datasets. However, their performance on detecting small objects or undistinguishable objects in visible spectrum images is still insufficient. In this study, we propose a novel detection algorithm for military objects by fusing multiple images using CNNs. We combine spatial, temporal and thermal information by generating a three-channel image, and they will be fused as CNN feature maps in an unsupervised manner. The backbone of our object detection framework is from the fast R-CNN algorithm, and we utilize cross-domain transfer learning technique to fine-tune the CNN model on generated multi-channel images. In the experiments, we validated the proposed method with the images from SENSIAC (Military Sensing Information Analysis Centre) database and compared it with the state-of-the-art. The experimental results demonstrated the effectiveness of the proposed method on both accuracy and computational efficiency.
Smart City Air Monitor uses air quality sensor attaching to the vehicle to monitor the air quality through out the city. This idea originally came from Pigeon Air Patrol, where they use pigeon to monitor air quality in London. We believe that using our own cars would have much better results. A pubnub will be sending push notifications for those who enters the polluted areas. It would provide 3 major benefits
1) For the drivers, they can now avoid heavily polluted areas and find alternative routes, it also allows them to monitor pollution during time of the day.
2) The drivers now are also providing the air quality data to the city so that everyone else can plan their days around it.
3) The city now knows where the most heavily polluted areas are, so that they can install air filters, trees, or simply signs to warn other citizens the general air quality around that area.
Embedded vision systems
I'm a researcher who's PhD is in the area of Digital Actors (mainly for videogames/interactive storytelling). So I'm looking at technology that will help drive advances in Digital Actor behavior and production.
Currently working on an Augmented IOT solution that involves AI
Today I'm at Constitution Hill Johannesburg, attending Water Hackathon and building water-saving system. It's gonna be awesome.
Car Breathalyzer System intergrated with facial and speech recognition
I would like to develop an AI that will teach students in Rural Niger-Delta of Nigeria (precisely in Emu Kingdom) where there are not enough teachers to teach them certain subjects. This will involve culture conducive AI tools and delivery.
My name is Filip and I recently started my amazing adventure with artificial intelligence and I am loving it! I have lots of ideas for making life easier or at least more amazing and breathtaking. My main goals are to make AI's for medical purposes like identifying tumors, etc. Automated self driving cars, face identification and more. Also I am hobbyist game developer and in this area, there are lots of things to push AI into. At the moment I am working on a program which can identify a brain tumors from MRI's photos. I am super excited for working in AI area and hope that I am going to achieve these goals.
Have a nice day guys and I wish you good luck with your projects.
Sorry if it is shocking for you :( but as an engineer working in automotive Industry I deeply feel myself responsible about it: According to WHO statistics, there are yearly around 1,2 million deaths in roads all over the globe. It means daily ~3500 people are lost. A very needed usage of AI is developing algorithms and designing systems which help drivers avoid mistakes. My dream project is something which will be installed on autos and reduces the number above.
If you are also interested in this topic I would like to be in contact with you, share what I know and know what the others think/do.
the images of this decreiption : http://monotonecritic.com/wp-content/uploads/2017/06/Advanced-Driver-Assistance-Systems-ADAS-Market-e1498045162384.jpg
No users to show at the moment.
No users to show at the moment.