Given a suitable dataset, transfer learning using deep convolutional neural networks is an effective method to develop a system to detect and classify objects. Despite having models pretrained on large general-purpose datasets, the requirement to manually label an application-specific dataset remains a limiting factor in system development. We consider this wider problem in the context of the purity analysis of canola seeds, where end users wish to distinguish species of interest from contaminants in images taken with optical microscopes. We use a Detector network, trained only to detect seeds, to help label the dataset used to train an Analyzer network, capable of both seed detection and classification. We present results, over three experiments that involve 25 contaminant species, including Primary and Secondary Noxious Weed Seeds (as per the Canadian Weed Seeds Order), to validate our incremental approach. We also compare the proposed system to competing ones in a literature review.
Annotation and analysis of sports videos is a challenging task that, once accomplished, could provide various benefits to coaches, players, and spectators. In particular, American Football could benefit from such a system to provide assistance in statistics and game strategy analysis. Manual analysis of recorded American football game videos is a tedious and inefficient process. In this paper, as a first step to further our research for this unique application, we focus on locating and labeling individual football players from a single overhead image of a football play immediately before the play begins. A pre-trained deep learning network is used to detect and locate the players in the image. A ResNet is used to label the individual players based on their corresponding player position or formation. Our player detection and labeling algorithms obtain greater than 90% accuracy, especially for those skill positions on offense (Quarterback, Running Back, and Wide Receiver) and defense (Cornerback and Safety). Results from our preliminary studies on player detection, localization, and labeling prove the feasibility of building a complete American football strategy analysis system using artificial intelligence.
Golf players spend hours perfecting their swing. It takes much practice and dedicated effort to train their body to make an effective swing. In order to train the body in such a way, golf players must be extremely mindful about the placement and motion of key body parts, such as wrists, elbows, shoulders, and torso. With correct placement and motion of key body parts, golf players can achieve great accuracy and consistency in their swings. In this research, we build on our previous work in evaluating the quality of a golf swing. Using a deep neural network, we are able to analyze a golf swing video, determine if it was an effective or ineffective swing, and provide feedback about the specific body parts that need improvement. This feedback can be used to improve player performance. Using this system consistently, a golf player can train their muscles and swinging technique.