Bird-scaring lines (BSLs) are an essential on-vessel bycatch mitigation device to reduce seabird interactions with fishing gear, such as the baited hooks of longline vessels. To ensure compliance with the behaviours required to operate successful BSLs, Electronic Monitoring (EM) cameras installed on fishing vessels can facilitate monitoring of commercial fishing activities. This study proposes an Artificial Intelligence and Machine Learning (AIML) framework based on a state-of-the-art deep learning computer vision approach called Faster RCNN to detect BSLs using vessel Electronic Monitoring (EM) video footage. The experiments include comprehensive analysis for detecting BSLs during daytime and night-time using footage from tuna longline vessels, under various weather conditions. Results show that a detection precision of 0.87 can be achieved. This valuable AIML tool can significantly reduce the time and costs associated with reviewing human EM footage, expand coverage, and automatically identify events for compliance checks and endangered species monitoring.