Rohan Sanil and Jinjun Wang are the founders of Deep North, they founded the company in 2016 to enable businesses to digitize their physical environments. Rohan has 20 years of strong experience in product and business and Jinjun Wang has 15 years of research and development experience in multimedia computing, computer vision and pattern recognition.
What is the USP of the Deep North ?
Existing video analytics companies employ facial recognition to track a consumer’s behaviour across physical venues; however, due to privacy restrictions such as GDPR and CCPA, such software cannot be used without the consumer’s agreement because it maintains personally identifiable information (PII). As a result, most vendors deployed in the West, concentrate on analysing and identifying items from a single point of view, such as an entrance doorway or a check-out counter.
Deep North’s major competitive advantage is its reidentification patent, which employs skeletal-based tracking algorithms that separate each unique skeleton into 124 distinct vectors. The combination of these vectors, comparable to a fingerprint, is unique to each individual and is subsequently saved in our cloud database as an anonymized hash code. We can track individuals across multiple cameras using this algorithm because we can re-ID each skeletal with their encrypted hash code when they move from one camera angle to another – allowing us to stitch together a customer’s journey from arrival to depart in a completely GDPR-compliant manner without storing any PII. This kind of multi-layered data is far more beneficial for organizations since it allows them to comprehend the whole client journey for different cohorts.
Tell us about the product, services, and solution that your company offers?
Deep North’s end-to-end software solution combines artificial intelligence with computer vision to help retailers and a business digitize and analyse behavioural metrics in the physical world and gives them tools to act upon these insights. Deep North’s proprietary entity detection platform enables our customers to derive behavioural insights such as store footfall, queue wait times, and conversion through our custom dashboards. Deep North’s reidentification and cross camera tracking technology enables us to provide shopper journey insights such as dominant paths and cross conversions. We work with a wide range of Global 2,000 customers in sectors such as Fashion Retail, Supermarkets, and Shopping Malls.
Where does Artificial Intelligence stand in the retail industry ?
Retail has been witnessing undercurrents of changes over the last decade. With rise of online players, Retailers started speaking about embracing omnichannel playbook and phygital transformation. However, this was more of talk and less backed by actions partly because technology was simply nascent in supporting the ambitions of brick and mortar stores. The pandemic has further exposed the glaring inadequacies of a traditional retail setup in providing a seamless customer experience. The challenge in a physical environment is indeed multi-fold and we are entering a stage of retail renaissance powered by a convergence of technologies.
One of the enablers is Artificial Intelligence that can provide the insights for both operational and strategic decisions. With the current AI advancements especially in the subfields of computer vision and deep learning, retailers can access rich granular information going beyond the POS transaction data and the traditional door counting. Businesses can understand the challenges at each of their stores and empower their in-store teams with real-time insights such as footfalls by day and hour, dwell times across different zones, POS conversions from zone, alerts to open additional check-out lanes, etc. The scope is immense for businesses to create customised use-cases and that’s exactly an area where both the challenges and opportunities lay.
How does Deep North’s video analytic platform work?
Deep North value proposition lies in leveraging existing CCTV cameras. In an on prem edge based deployment scenario, the video data are processed on site to generate rich metadata to detect objects and assign unique ids to them.
The inference pipeline brings together camera feeds meta data and algorithms for real-time processing on the cloud. The algorithms in inferencing pipeline will generate rich metadata about physical environments such as engagement, pathing, and dwelling. The metadata is then rerouted in the form of insights to the dashboards and mobile apps in Deep North platform with less than a second of latency. In case of cloud deployment, the video processing happens on the cloud. The entire platform is designed for privacy compliance as metadata cannot be linked to PII data.
What are the markets that Deep North caters to?
Deep North’s customer base spans across Retail, Shopping Centres, Quick Service Restaurants, Transportation, Commercial real-estate, Manufacturing, and Warehouses. We help to improve operations and create exceptional customer experiences in the store or across the entire chain using real time video analytics.
Deep North is currently operational across the globe with deployments in the North America, Europe, Middle East and South East Asia. We have recently set up our Mumbai Office since March this year with the focus on educating enterprises in APAC market on the value that intelligent video analytics can bring to the table.
What is the Impact of AI Video Analytics on Business Operations
Instead of simply terming AI, we prefer to use the term Intelligent Video Analytics. Because that truly accentuates with what the technology intends to do. At its core, Intelligent video analytics technology gives direct line of sight to what is working, and what isn’t in one’s retail space. In a sense, it empowers businesses by giving complete ownership into the physical environment.
Armed with actionable alerts, insights, recommendations, and predictive analysis, Retailers are able to optimize in-store operations, reduce waiting times, prevent cart abandonment, ensure personalised attention to customer in high value merchandise areas, maximise marketing and promotional impact etc. The basket of use cases for Shopping centres expands as they can track customer footfall patterns throughout the day, monitor circulation throughout the mall, assess health of tenant mix, optimise leasing strategies etc. To summarise, there is a clear pathway to ROI that can be continuously nurtured and developed in consultation with each enterprise.
What are the future plans of the Deep North?
We have big goals for democratizing computer vision usage globally. The effectiveness and computational power of deploying computer vision-based systems continue to grow significantly year after year as companies like NVIDIA continue to invest billions in improving GPU microarchitecture. Additionally, if 5G network infrastructure is implemented at scale, it becomes more practical to use off-premise architecture since video feeds from cameras can be transferred directly to the cloud.
These developments allow Deep North to further serve a wider range of customers since we can easily and cheaply light up their stores overnight. We are thus ramping up our attempts to broaden our geographic reach outside the West to include places like the Gulf, India, and Southeast Asia.
By implementing our solution with businesses in every new region, we are able to create fresh use cases from businesses with various needs and views while also training and enhancing the accuracy of our algorithms in those new contexts.
Few words about Techiexpert
We are very excited to reach out to industry stalwarts, researchers, technology professionals, enthusiasts through the wide readership of Techiexpert. At Deep North, we envision ourselves as an accelerant to adoption of privacy compliant computer vision technology in consumer facing enterprises. This requires a concerted effort in educating enterprises and customers alike. We are all in this together and to effectively surmise, platforms like Techiexpert as part of the bigger AI ecosystem play a pivotal role to forward the convergence of technologies to create an overall enriching human experience.