Heated and immature canola kernels caused by excessive drying and frost damage are undesired by grain buyers due to low oil yield, hence its presence above a certain threshold brings down their market value. These damages are identified by analyzing the endosperm colour which is different for healthy and damaged kernels. The current method employed for determining the damage is by visually examining the endosperm colour, and then counting the number of damaged seeds, which is laborious, time-consuming, and highly prone to both human and sampling error. This study proposes a three-stage deep learning based computer vision technique to detect, track, and count the damaged canola seeds in real time. The detection task was done using a YOLOv7 object detection network to localize and classify immature and heated seeds, which was trained on an annotated dataset containing 1500 instances. The detection weights obtained from the network were then inputted into a multiple object tracker to track the detections frame by frame and generate unique IDs which were then used to count the number of defects. The combined detector and tracker model counted the number of damaged kernels in an unseen video with good accuracy and an average inference speed of 24 FPS. Thus, the proposed system can be readily deployed in an edge device for accurate and real-time grading of canola kernels by grain buyers.

The Canadian food waste (fruits and vegetables) is 90,600 tons from a total production of 3,048,143 metric tons in 2018 (FAO, 2022). Fruit and vegetable production in Canada increased to 3,208,388 metric tons in 2022 (StatCan, 2022), therefore food waste is also anticipated to have increased in recent years seeing the trend of past years and increased population. Additionally, food waste also includes leftover foods in the food industries, restaurants, kitchens, spoiled foods from grocery stores, or landfills, that contributes to global warming by producing greenhouse gases. Therefore, valorization of food waste to green energy in form of biofuels is an alternate approach to overcome aforesaid problems. Current research details the physicochemical characteristics of food wastes obtained from a typical university restaurant and their potential to be used as biofuel. The moisture content of the samples (brussels sprouts, pumpkin, carrot, parsnip, beet, and celery) varies from 79-93 % (wb). Hydrothermal liquefaction (HTL) process is a thermochemical depolymerization process in an enclosed reactor to get biocrude oil from wet biomass, where the reaction temperature varies from moderate (200-380 °C) with high pressure (5-25 MPa). The proximate (ash, volatile matter, fixed carbon) and ultimate analyses (CHNS) of the food waste reveal that all samples have potential to produce biocrude, however, carrot and parsnip show the most because of their higher C (42.4-43.1%) and H (5.7%) contents. Furthermore, carrot have the highest cellulose (80.9%) and hemicellulose contents (9.1%) which makes it the suitable material for carrying out HTL reactions for higher biocrude yield.