Skip to main content
With the advancement of vision technologies, most industries are moving towards automatic safety monitoring systems for its enforcement. However, most of them are plagued by problems such as false detections and missed detections which are extremely costly resulting in wrong safety monitoring alerts and safety hazards. Also, unlike existing areas of object detection where there is the availability of large datasets, existing research works in detecting industrial safety gears have a problem of having large datasets to train. Our research helps address these challenges and at the same time aims to develop a unified industrial safety system that improves the identification of safety gears under complex conditions of illumination, posture and occlusions.
Click here, to know more in detail about ‘reducing memory of neural networks for IoT/Edge device’.
Decoupled Classification Refinement with Multistage Training Based Detector