Page 36 - Security Today, September/October 2021
P. 36

eras are ideal inputs and offer valuable data since they provide varying perspectives, unique environments and new unstructured data sets that many existing AI models are not based upon.
While Machine Learning is efficient because its algorithms are good at analyzing structured data, it’s ineffective at processing unstructured data. Therefore, as AI looks to perform more com- plex analysis of unstructured data, Deep Learning with its algo- rithms based on simulated neural networks, is more capable. Visual data—including raw visual data in computer vision and encoded images or videos in JPEG and H.264/265—is unstructured data and incredibly valuable to Deep Learning. As we know, the Se- curity Industry as a whole presents an abundance of visual data in real-world use cases—data that will undoubtably help drive ad- vancements in Deep Learning over the next few years.
Despite the promising advancements in AI, it’s important to set ex- pectations around what AI can and cannot do. For example, many analytics use image classification to detect people and vehicles, but that doesn’t equate to actually understanding a scene. Visual under- standing is still very challenging and currently there is not enough re- al-world data and applicable training to allow an AI-based solution to fully understand a scene. Furthermore, the best AI-based analytics are not able to read a person’s behavior. Emotional differentiation such as humor is something that an AI-based solution cannot de-
“As a result, many industries are now starting to realize the significance of both hardware and software when applying AI to more real-world use cases.”
termine or infer. In a scene where crowds gather, AI-based analytics cannot understand if the event is an altercation or a celebration.
Clearly there are still some tough questions that face our in- dustry when it comes to real-world applications and possible AI- solutions for our customers. For these reasons, analytics used in the security industry require some degree of human interaction and judgement. In addition to these considerations, vulnerabil- ities exist in data manipulation of neural networks, which can cause AI to output inaccurate results. For instance, you cannot fully understand a scene at the single pixel level, so there is still work to be done from a technological standpoint.
This fact can also be illustrated by the dynamic nature of im- ages captured on an IP camera—in a scene where lighting is in- consistent, harsh shadows can cause changes in a per pixel level that affect the classification of an image or object. All that said, the community of AI developers is growing and they, in combina- tion with their partners, are making great strides.
Untitled-2 1

   34   35   36   37   38