This paper presents a method to detect unlabeled malaria parasites in red blood cells. The current "gold standard" for malaria diagnosis is microscopic examination of thick blood smear, a time consuming process requiring extensive training. Our goal is to develop an automate process to identify malaria infected red blood cells. Major issues in automated analysis of microscopy images of unstained blood smears include overlapping cells and oddly shaped cells. Our approach creates robust templates to detect infected and uninfected red cells. Histogram of Oriented Gradients (HOGs) features are extracted from templates and used to train a classifier offline. Next, the ViolaJones object detection framework is applied to detect infected and uninfected red cells and the image background. Results show our approach out-performs classification approaches with PCA features by 50% and cell detection algorithms applying Hough transforms by 24%. Majority of related work are designed to automatically detect stained parasites in blood smears where the cells are fixed. Although it is more challenging to design algorithms for unstained parasites, our methods will allow analysis of parasite progression in live cells under different drug treatments.

In this paper we address the issue of autonomous navigation, that is, the ability for a navigation system to provide information about the states of a vehicle without the need for a priori infrastructures such as GPS, beacons, or preloaded maps of the area of interest. The algorithm applied is known as Simultaneous Localisation and Mapping (SLAM). It is a terrain aided navigation system which has the capability for online map building, while simultaneously utilising the generated map to bound the errors in the navigation solution. As no a priori terrain information nor initial knowledge of the vehicle location is required, this algorithm presents a powerful navigation augmentation system. More importantly, it can be implemented as an independent navigation system. This paper also describes a decentralised SLAM algorithm which allows multiple vehicles to acquire a joint 3D map via a decentralised information fusion network. The key idea behind this decentralised SLAM is to represent the map in information form (negative log-likelihood) for communication. Experimental results are provided using computer simulation to demonstrate the single-vehicle and multi-vehicles SLAM without the use of GPS and preloaded maps.

No abstract