Enhancing Workplace Health & Safety Using Computer Vision

- Subhash Sharma 

Although health and safety at workplaces have improved over the years, yet the UK continues to have a large number of workplace accidents. The number of accidents resulting in injury, or in some cases, even death is quite high. Many of these accidents can be avoided, and AI-based computer vision can play a significant role in cutting down these accidents. 

Health and Safety Statistics. Key figures for Great Britain (2018/19)

• 1.4 million working people suffering from a work-related illness
• 2,526 mesothelioma deaths due to past asbestos exposures (2017)
• 147 workers killed at work
• 581,000 working people sustaining an injury at work according to the Labour Force Survey
• 69,208 injuries to employees reported under RIDDOR
• 28.2 million working days lost due to work-related illness and workplace injury
• £15 billion estimated costs of injuries and ill health from current working conditions (2017/18)

( Source: https://www.hse.gov.uk/statistics/ )
Forklifts alone account for 1,300 UK employees being hospitalised each year (That’s 5 UK workers each workday!) with serious injuries due to these accidents. Unfortunately, that number is rising as there is a significant growth in e-commerce and warehouses across the UK. 

Use of AI-based computer vision for optimising workplace health and safety in the UK.

Our Computer Vision product, IRIS, is an AI-based computer vision solution to track and predict workplace accidents and then prevent them from happening. The existing use cases include:

• Fork Lift Safety, Predicting and Prevention of Fork Lift accidents.
• Use of Lifting Equipment
• Work at Height
• Fire & Thermal injuries and accidents
• Machine Guarding
• Manual Handling
• Monitoring near misses and reporting near misses & accidents in real-time
• Monitoring Use of PPE

IRIS is an enterprise computer vision solution. The product is currently deployed at many customer sites including Fortune 500 companies. The AI solution sits on the top of existing CCTV infrastructure. It is very cost-effective and can be deployed quickly either at a customer site or through the cloud. 

Get in touch with us to know how we can make workplace safer for your employees.

Competing in the Age of AI

-Apoorva Verma

How machine intelligence is changing the rules of business and what should companies do to stay on top? 

Pic: Freepik

Artificial intelligence (AI) is a branch of computer science that makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks.

According to IDC, companies are forecast to spend $98 billion on AI, globally in 2023. This stems from the fact that more and more businesses continue to invest in projects that utilise the capabilities of AI software and platforms. For example, most companies have turned to chatbots or automated customer service agents for their customer services.

In the current scenario, the world is grappling with a global pandemic, the COVID-19. This has forced most of the countries into lockdown and changed the way businesses function. The role of AI has now become more important than ever.

We are in a phase where AI is realising its potential in achieving human-like capabilities, so isn’t it time to question the business leaders on how they can harness the strength of man and machine.

With technologies such as deep learning, IoT, computer vision and language processing, machines have learnt how to speak, read, text, identify patterns, and so much more. As this field precipitates more into commonly manual activities, for example, the use of AI to combat the corona pandemic in many countries such as training the AI to recognise a positive case using the Chest X-Ray or using drone cameras for thermal screenings.

THE COMPETITIVE ADVANTAGE:

Rather than scrapping the traditional methods of competitive advantage, AI reframes them in such a manner that companies can get a dynamic view of their strengths. For example, the health and safety of company employees were traditionally dependent on manual hours of patrolling security, it then moved to long hours of video feed monitoring from multiple cameras. However, humans are prone to error due to fatigue or negligence.

So, how can this be reimagined by AI?

• Data: AI can harness data at a much faster rate and directly from users. 
• Automation: Algorithms learn from data and experience. This allows us to train them for any security breaches as well as to explore new opportunities that may not be possible manually.
• Decision Making: AI increases the rate and quality of decision making as the number of inputs and the speed of processing for machines can be millions of times higher than for humans. 

Thus, AI can make lives safer and help employers gain insights on those areas that may have been opaque to them before. Our computer vision solution, IRIS AI is certainly changing lives and supporting business restart their operations.

Furthermore, predictive analytics and objective data are free from human gut feeling and experience. Many industries such as manufacturing, warehousing, retail, banking, automobile and many more have all moved sharply towards adapting computer vision technology. For example, in retail, AI can generate insights from online as well as physical stores (if connected using computer vision).

CONCLUSION:

In this AI-enabled world, it is almost imperative for companies to embrace AI to achieve a competitive edge. Companies need to identify what machines can do better than humans and vice versa, and then develop complementary roles and responsibilities for each, and redesign processes accordingly.

IRIS AI – A fight against the COVID-19 Pandemic

pic: Unsplash 

How do we stop a global pandemic which has infected over 3.6 million and claimed more than 250000 lives? 

As the number of COVID-19 cases continues to rise, wearing masks and gloves, frequent hand sanitization, social distancing, and early identification of infected people are crucial in curbing further spread of COVID-19.

However, the biggest challenge that is faced by organizations is to enforce and ensure strict compliance with these measures. Especially at a time when the number of cases is on a surge each day, non-compliance due to human negligence and fatigue can cost us greatly.

To put it in words, “we are our worst enemies” during the COVID-19 pandemic.

This is where technology such as computer vision can be highly impactful. IRIS AI, a flagship product by Integration Wizards Solutions can transform your passive CCTV cameras into active analytical tools.

The computer vision technology can keep your employees and premises safe by ensuring the use of masks and gloves by people, social distancing compliance, and early sensing of fever using thermal cameras.

With the majority of countries in a lockdown, business continuity is another key challenge being faced by companies across the globe. However, it is also critical to get the operations re-started to get the economy back up.

So, for those looking for an effective mechanism of ensuring more than 99% compliance without any infrastructure overhaul, implementing IRIS computer vision can help.

IRIS AI uses the feed from existing CCTV to detect non-compliance and raises real-time alerts as SMS, WhatsApp messages, email, etc. The alarm is configured to be sent to the right authority who can then take the necessary steps like personally contacting the non-compliant employee. Moreover, it gives insights on a dashboard for the organisation to understand the analytics during a given time period.

In these challenging times for communities across the globe, technology and innovation could be the key in this fight against COVID-19.

Looking Back: The best of 2019

“If you are not prepared to risk the usual, you will have to settle for the ordinary” – Jon Rohn

This year saw substantial growth in artificial intelligence and computer vision adaptation as well as the demand to keep up with the technology and innovation in businesses. These were the key drivers that kept us going, and also continue to motivate us for the upcoming decade.

We completed six years and successfully graduated from the start-up club to become an enterprise. From receiving ISO certification and Nasscom membership to getting recognised by Google amongst a handful MDM providers, it was a year to be proud of.

Our revenue has propelled eight times and we have on-boarded about twenty clients in the last six years. Working with our strategic partners Nvidia & Microsoft, we cracked the code on machine learning and many from our team up-skilled. We developed algorithms to control automated drones and upgraded for our client goals.

Our product is being used by 20,000 users across the globe and we actively participated in global conferences in the US, Spain and India. We grew not only in talent, but numbers too. A start-up that began with five now has about 65 members and a 7000sq. Ft of state of the art development centre in India.

Another feather to our cap came with the addition of seven Fortune 500 companies such as PostNord, Dover, Heineken, Xerox to name a few. Moreover, our AI-powered computer vision product, IRIS is now the synthetic intelligent eye for some corporate giants that include one of India’s largest solar plants, automobile manufacturer, chemical manufacturer, jewellery retail chain, construction corporate, heavy engineering, as well as FMCG. Last but not least, we also made some great improvements to our website – that’s right, we had a revamp of our website.

And we are not stopping here. We are striving to achieve more associations, more growth in 2020. 

#2020goals #yearendreview #sixyears #anniversary

Moving towards an AI-enabled future

McKinsey Global Institute claims that artificial intelligence is contributing to a transformation of society 10 times faster and at 300 times the scale, or roughly 3000 times the impact of the Industrial Revolution.

This is observed by the upsurge in artificial intelligence and computer vision adaptation as well as the demand to keep up with the technology and innovation in businesses in the last few years. According to a report by IDC, aggressive investments have been made in cognitive and AI solutions and in fact, global investments are expected to reach $57.6 billion by 2021.

Such investments are catalysed by the advent of modern computer vision and image processing techniques. AI-powered computer vision coupled with hardware-based accelerators have opened up the possibilities of analysing images in real-time to identify objects and activities. 

Since, a typical CCTV image is more than 100,000 Bytes, in this context, it might be quite apt to surmise that a picture is worth hundred-thousand words! 

At present, there are over 500 million CCTV cameras installed and the number is expected to rise to over a Billion by 2021. While these cameras cover everything from manufacturing, yards, warehouses, retail outlets to several parts of modern cities, so far they have been used retrospectively for monitoring and forensic analysis.

However, there is substantial growth in their usage in various verticals. For instance, retail outlets are getting equipped with the capability of knowing their customer demographics, dwell time and even emotions. Even the government is contemplating their use in smart city initiatives as they could prove beneficial if suspect activities are filtered from the live CCTV footages. Likewise, manufacturing premises bolster their safety parameters by ensuring any hazardous non-compliance is actively analysed and reported. 

In fact, stepping up occupational health & safety for people at all levels is the new benchmark that some of the companies are trying to work towards. If this becomes a norm, it could make a sustainable difference in global OSH challenges and promise a brighter future. 

Thus, an AI-enabled future lies in the best use of distributed vision technologies while delving into the deeper end of machine learning and deep learning to explore and understand the potential of these technologies better.

If you are looking to explore how computer vision technology can be useful in your enterprise, check out IRIS AI by Integration Wizards Solutions.

Computer Vision: Enhancing Industrial Safety with AI

by Apoorva Verma

The AI revolution is here.

As artificial intelligence increasingly gains prominence, several sub-domains such as computer vision, machine learning, deep learning, internet of things, and analytics are some of the technologies that have propelled growth.

Out of these, computer vision is one of those technologies that enable the interpretation and understanding of the visual world for machines. With the help of digital images and deep learning models, computers react to what they 'see' by identifying and classifying objects. In fact, accuracy rates in recognising and responding to visual inputs for the technology has risen from 50% to 99% over the past decade. This means that such solutions could become indispensable for a range of applications across industries.

However, our focus of discussion is the use of computer vision technology in manufacturing, which now have the necessary means to achieve automated safety compliance.

A Computer vision solution, such as the IRIS, developed by Integration Wizards, to work with an existing CCTV network, would serve as an advanced and effective replica of the human eyes, with the added ability to identify and classify different objects or situations, and react accordingly, such as in the form of alerts.

For instance, the AI-powered solution ensures workforce safety compliance by identifying workers without prerequisite safety equipment or protective gear such as hardhats, visibility vests, etc. This results in an appropriate response, like sending a real-time notification to the safety manager. The solution also maintains a database of safety protocol breaches which would be useful in investigations of any workplace accidents as well as take a step towards preventing accidents.

The application of the solution further extends from safety gear detection to occurrence of serious incidents such as the detection of fire and electrical malfunction, machine malfunction, trespassing or unauthorised access to hazardous areas, etc.

Efficient response trigged from the system in such scenarios aids in preventing serious losses to the workers as well as the manufacturing plant. Thus, it detects any anomalies that are not in accordance with the standard operating procedures. Real-time alerts and fail-safe measures accelerate the resolution of the issue.

The application of the solution can further encompass operational safety compliance. This would include material safety, such as the multi-object detection through computer vision, with automatic scanners on production lines, etc. In addition, it would identify any faults with raw materials that may be too small for the human eye but could prove detrimental for the final product.

In high performing manufacturing plants, compliance with safety regulations becomes the utmost priority. In fact, components falling off the production line must also adhere to safety guidelines.

Ultimately, the pressure of delivering high quality, efficient and time-sensitive results at manufacturing premises, together with the use of heavy machinery, potentially dangerous equipment, and the possibility of human error, make such sites prone to oversight of safety compliance, and by extension, workplace accidents.

Such unique innovative solutions can ensure safety compliance across the workforce as well as the entire manufacturing process and facility.

What it takes to be a Deep Learning Engineer

By Akash James

The race for AI will dwarf any other race relative to the mystic realm of technology”.

No, I’m not quoting anyone, just saying what I often tell myself.

Most people just see technology as a creature comfort, but throw on my shoes and put on my spectacles and you’ll see art that just lures you in to be an artist. The wheel was the best invention in my opinion and has stayed that way since 3500 B.C. Fast forward over 5 millennia later and we still use this humble yet irreplaceable invention. But hey, why not create a new contender to the wheel (My narcissism is preceding me right now!), something that interweaves into human existence; like a cybernetic triple helical DNA structure where the third strand would be of Extended Intelligence. Yes, I didn’t say Artificial Intelligence, rather Extended where our capabilities have been enhanced with our own creation. Intelli-ception, maybe?

When I began my engineering, I had a plethora of technologies to amalgamate my consciousness in. I’ve had my fair share of experience with android apps, robotics and the Internet of Things, but just as I was walking through this Odin’s Vault of technology, I stumbled upon the Infinity Gauntlet of Artificial Intelligence, Deep Learning. With my eyes immobilized on it, I went ahead to wield the gauntlet and snap something awesome into existence once I had all my infinity stones. Of course, the infinity stones is just an analogy to things like Neural Networks, Algorithms, Math and so on. Boy, oh boy, getting the infinity stones is no joke.

After completing engineering with a bunch of projects that had deep learning coursing through its CUDA cores, I joined Integration Wizards Solutions. Again, with an Azure Hackathon as a stepping stone, I was bestowed with the opportunity to flex my fingers with the gauntlet and weave solutions laced with deep learning. This is where I exploited Object Detectors to arguably detect a variety of object instances that would verify compliance, MTCNNs to recognize people and keypoint detection for Pose Estimation. This product is what we call, IRIS.

Initially, it began with training models and getting our algorithms to work in a controlled environment; Proof-of-Concept, what my folks at work and a lot of you call it. But then the production level stuff began. At times it felt like you’re in a cave and you need to create a miniaturized arc reactor in a fortnight. Train models, code the business logic, design functionality, unit test, optimize, refactor and scale for load are some of the steps in chronological order. Being a Deep Learning engineer requires a lot of ingenuity and rationing of your time.

C'mon, I need 21 minutes every day to watch my favourite anime. Where else will I derive the power of will made of steel that enables me to not give up?

Given the nature of trial-and-error when training models, it takes a lot of clever decisions (what we call hacks) with respect to dataset augmentation and hyper-parameter tuning to trick neural nets to do what we want them to do. Sorcery it is! Scaling is where all the roadblocks begin. One challenge we faced was creating a pipeline that could accommodate 200-odd cameras for real-time object detection inference.

There was a need for speed and accuracy was a priority. The resultant was a neural network that was very demanding. We countered this with 6 NVidia RTX 2070s, a Flask Server powered by Gunicorn, TensorFlow and a pinch of awesomeness. We used TensorRT to run an optimized frozen INT8 graph at 100+ fps.

When deploying this, you don't want to accidentally create Ultron that goes rogue and raises false alarms (No strings attached is a bad thing, trust me). With a tad bit of Computer Vision techniques into the mix, we were able to solve the false alarms. Another project required us to combine tracking and detection together for Intrusion Detection. Detection was GPU intensive and tracking was CPU extensive, a balance was needed to share the load and run in the most optimal manner.

This experience led me to believe that mastering the art of Deep Learning involves mastering other elements of technology. Be it writing APIs that serve inference, multithreaded code for increased throughput or networking to handle a multitude of input sources.

Every day there is a call for code, a new mountain to conquer, a new challenge to accomplish. With new infinity stones I collect, it brings me one step closer to completing the masterpiece I envision, a contender that'll give the humble wheel a run (rather, a roll) for its money, all built on the shoulders of Extended Intelligence. *snap*