Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness

Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness

We proposed a novel object detection framework using image fusion and convolutional neural networks (CNNs) for the military scenario.

Robotics, Artificial Intelligence

  • 0 Collaborators

  • 0 Followers

Description

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.

Gallery

Medium 23674745 538901773125884 7636566904215259396 o

Rima M. updated status

Medium 23674745 538901773125884 7636566904215259396 o

Rima Modak

I am currently working to develop a prototype of an device based on IoT. This device will be used to detect any kind of material. It will be used to detect both living and non-living things, and after detecting, it will display varies other things related to the detected object according to the tags provided by the user/customer.

Medium fb img 1503828642929

Aravindhan N. created project Automatic attendance management system using face detection

Medium 5ad5deff 1bd2 4f42 8706 11bcd0116743

Automatic attendance management system using face detection

Automatic attendance management system will replace the manual method, which takes a lot of time and is difficult to maintain.There are many bio metric processes ,in that face recognition is the best method. In our campus staff attendance is taken with the help of Gesture recognition /attendance sheet .We can take this to next level by implementing Artificial Intelligence based Face Recognition using Convolution Neural Network(CNN). We have to train our neural net using COCO (large Image dataset designed for object detection) and Staff Dataset (Several images of individual staffs). Since we don't have the photos of the staffs,we have trained our neural net using our own photos.Our Neural net consists of 20 neurons in the hidden layer which help us to diagnose the pixels of the image and compares the result with the trained dataset .By using our advanced system the staffs can use their own mobile/laptop [camera] for registering their presence in their own place which is possible only if they are connected to our college Network (WiFi).

See More

No users to show at the moment.

No users to show at the moment.