Browsing by Author "Lal, Kartikay"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A novel approach to recognition of the detected moving objects in non-stationary background using heuristics and colour measurements : a thesis presented in partial fulfilment of the requirement for the degree of Master of Engineering at Massey University, Albany, New Zealand
    (Massey University, 2017) Lal, Kartikay
    Computer vision has become a growing area of research which involves two fundamental steps, object detection and object recognition. These two steps have been implemented in real world scenarios such as video surveillance systems, traffic cameras for counting cars, or more explicit detection such as detecting faces and recognizing facial expressions. Humans have a vision system that provides sophisticated ways to detect and recognize objects. Colour detection, depth of view and our past experience helps us determine the class of objects with respect to object’s size, shape and the context of the environment. Detection of moving objects on a non-stationary background and recognizing the class of these detected objects, are tasks that have been approached in many different ways. However, the accuracy and efficiency of current methods for object detection are still quite low, due to high computation time and memory intensive approaches. Similarly, object recognition has been approached in many ways but lacks the perceptive methodology to recognise objects. This thesis presents an improved algorithm for detection of moving objects on a non-stationary background. It also proposes a new method for object recognition. Detection of moving objects is initiated by detecting SURF features to identify unique keypoints in the first frame. These keypoints are then searched through individually in another frame using cross correlation, resulting in a process called optical flow. Rejection of outliers is performed by using keypoints to compute global shift of pixels due to camera motion, which helps isolate the points that belong to the moving objects. These points are grouped into clusters using the proposed improved clustering algorithm. The clustering function is capable of adapting to the search radius around a feature point by taking the average Euclidean distance between all the feature points into account. The detected object is then processed through colour measurement and heuristics. Heuristics provide context of the surroundings to recognize the class of the object based upon the object’s size, shape and the environment it is in. This gives object recognition a perceptive approach. Results from the proposed method have shown successful detection of moving objects in various scenes with dynamic backgrounds achieving an efficiency for object detection of over 95% for both indoor and outdoor scenes. The average processing time was computed to be around 16.5 seconds which includes the time taken to detect objects, as well as recognize them. On the other hand, Heuristic and colour based object recognition methodology achieved an efficiency of over 97%.
  • Thumbnail Image
    Item
    Thin film electrochemical sensor for water quality monitoring : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Engineering, Massey University, Auckland, New Zealand
    (Massey University, 2023-12-11) Lal, Kartikay
    Freshwater is the most precious natural resource, essential for supporting life. Aquatic ecosystems flourish in freshwater sources, and many regions around the world depend on aquatic food sources, such as fish. Nitrogen and phosphorous are the two nutrients, in particular, that are essential for growth of aquatic plants and algae. However, with rising population and anthropogenic activities, excessive amounts of such nutrients enter our waterways through various natural processes, thereby degrading the quality of freshwater sources. Elevated levels of nitrate-nitrogen content, in particular, lead to consequences for both aquatic life as well as human health, which has been a cause for concern for many decades. As recommended by the World Health Organization, the maximum permissible nitrate level in water is 11.3 mg/L. These levels are often exceeded in coastal areas or freshwater bodies that are close to agricultural land. Therefore, it is essential to monitor nitrate levels in freshwater sources in real-time, which can be achieved by employing detection methods commonly used to detect ionic content in water. Hence, a comprehensive review was carried out on various field-deployable electrochemical and optical detection methods that could be employed for in-situ detection of nitrate ions in water. The primary focus was on electrochemical methods that could be integrated with low-cost planar electrodes to achieve targeted detection of nitrate ions in water. Designing resilient sensors for real-time monitoring of water quality is a challenging task due to the harsh environment to which they are subjected. There is a significant need for sensors with attributes such as repeatability, sensitivity, low-cost, and selectivity. These attributes were first explored by evaluating the performance of silver and copper materials on three distinct geometric patterns of electrodes. The experiments produced promising results with interdigitated pattern of copper electrodes that were successful in detecting 0.1-0.5 mg/L of nitrate ions in deionised water. The interdigitated geometric pattern of electrodes were further analyzed in four distinct materials namely, silver, gold, copper, and tin with real-world freshwater samples that were collected from three different freshwater bodies. The water samples were used to synthesize varying concentrations of nitrate ions. The results showed tin electrodes performed better over other materials for nitrate concentrations from 0.1-1 mg/L in complex matrix of real-world sample. The nitrate sensor eventually needs to be deployed in freshwater bodies, hence a real-time water quality monitoring system was also built that incorporated sensors to monitor five basic water quality parameters with the aim to monitor and study the quality of water around the local area.