This thesis tries to find a solution for the problem of managing and monitoring the banana shelf in a supermarket using IoT. The research focuses on using a wireless sensor that detects some features of the banana shelf while being non-intrusive. The three main features that are examined of the shelf are the quality and quantity of the bananas and the quality of the shelf. First a research was conducted to find the best sensor to use for these measurements. The chosen sensor is a color image sensor, the platform for the IoT device is a Raspberry Pi. Using the python programming language in combination with the openCV library image processing was used to detect the features. The image is first smoothed using a Gaussian filter, afterwards the foreground is segmented. The different segmentation methods are researched and adaptive thresholding is used. To determine the quantity of the bananas and quality of the shelf the stickers on the bananas are detected. This detection is implemented using different filtering methods ranging from spectral filtering to color thresholding. With the segmented foreground the quality of the bananas is assessed using a color histogram. This information is then sent to a communication module that is connected to a IoT dashboard for user interpretation. With the proposed design the status of the shelf including the percentage of the shelf filled, the quality of the bananas on the shelf and the neatness of the shelf are available for a supermarket manager to better organize his supermarket. This sensor makes it possible to better organize the banana shelf and act preemptive instead of reactive.

People counting data in offices is used in many applications like HVAC system control and space management to increase comfort, decrease energy consumption and optimise space utilisation. In contrast to past approaches using imaging modalities that tend to be either expensive or intrusive, we consider single-pixel thermopile sensors for people counting. These sensors may already be deployed as part of a smart lighting system to provide temperature data for HVAC controls. Firstly, a statistical sensor model for thermopile temperature measurements is proposed. The proposed people counting method enhances the CUSUM RLS algorithm to estimate temperature change caused by people entering or leaving. We estimate mean temperature changes upon detection of an occupancy event, and then estimate the people count using a maximum likelihood on the estimated temperature change. Finally, PIR vacancy data is merged with the people count estimation to increase accuracy. We obtain an average counting error of 0.11 and 0.19 for 90% of the instants respectively when considering 15 minute windows for simulated and experimental datasets. A second aspect of the thesis considers the problem of commissioning plan detection. We leverage the two-sided CUSUM signals to address this problem. The two-sided CUSUM scores for a pair of sensors are used to calculate similarity measures; these features are used in a Random Forest Classifier to detect commissioning changes of the sensor pair. Using simulated data with the thermopile signal model, we show that the proposed method achieves a true positive rate (determining the correct layout) of 90.2% and false positive rate of 1.3%.