Logistics is one of the industries that Artificial Intelligence is making an ineffaceable mark on, creating boundless opportunities for software vendors to innovate in the space. Logistics companies today need intelligent smart warehousing technologies which becomes possible by applying the right algorithms to perform tasks like smart inventory, supply chain, transit prediction and security.
Knowledge Lens is an India-based product technology company that builds domain-specific Data Lenses that enable the discovery of actionable insights from Enterprise Data Assets. Our team of tech experts work on cutting edge technologies such as Big Data, AI, Blockchain and Cloud to add differentiated value to our customers. Our mission is to turn enterprises’ dark data into meaningful business insights.
Here’s presenting our customer case study on Perimeter Intrusion Detection for modern warehouses-
Client Introduction & Business Requirement:
Our client is a Global Logistics Company based out of India.
Catering to the increased demand in online retail, modern warehouses today face many challenges from sorting, tracking, transit operations to seamless delivery. Security risks are the most common challenges faced by them as these warehouses are usually set up in the outskirts of the city with proximity to transit hubs like railways, airports etc. Warehouses have multiple entries and exits which are frequently attacked by well heeled trespassers, leading to a great deal of loss for warehouse companies. Industry statistics show that warehouse locations remain as the most common place for cargo thefts. In order to avoid security threats like burglary, theft and vandalism, logistics companies today are looking for a highly advanced, technology-driven state-of-the-art infrastructure for their modern warehouses.
Our client wanted an increased security system for many of their warehouses. We were able to deliver a highly scalable and robust solution to them with our Perimeter Intrusion Detection System (PIDS) – which has an overall function of detecting the person attempting to gain unauthorized entry into the warehouse, identifying how long the person stayed unauthorized, capturing the image of the intruder and identifying suspicious activities (odd hours, scaling walls, unauthorized package removal etc.) around the warehouse premises.
Perimeter Intrusion Detection is essential in protecting critical assets and resources in a warehouse. In case of detecting unauthorized physical access, the algorithm is fed the video stream directly from the source, it detects and raises an alert about the presence of any suspicious entity. The solution detects intrusion and raises a suspicious alarm to notify the security guard or the security command center.
A unique combination of Intel’s powerful hardware and the latest AI driven innovation helped us build a robust solution for our customer. Firstly, we planned to optimize the cost through efficient use of hardware and our approach to scalability issues. While working with the Intel AI Builders technical team, we developed an Intel compatible AI model architecture and used the Intel Open VINO toolkit to optimize the resource hungry models. Optimizations helped improve the inference performance on Intel® Xeon® Cascade Lake by leveraging the quantization capabilities available via DL Boost on 2nd Gen Intel® Xeon® Scalable processors.
We are now able to run a large number of models parallelly in the same machine, which means our architecture is now compatible to run up to 30 cameras. This has helped us to optimize cost and run more AI models with less number of servers.
· Reduced process or space consumption by 20-30%.
· Runs up to 30 parallel streams on a single machine.
· Cost reduction by 50-60% on hardware used.
· Core usage of AI models retained, without loss of accuracy.
At Knowledge Lens, we constantly work towards improving our product technologies, so your business can do more for you, We have partnered with Intel to bring AI to the center of your data-centric strategy and help business leaders augment their threat detection capabilities.
In case you have more questions feel free to drop me a mail at firstname.lastname@example.org or contact us here.