McMarvin Research AI Advancing AI for industry and society

McMarvin Research has been exploring artificial intelligence and machine learning technologies and techniques for decades. We believe AI will transform the world in dramatic ways in the coming years – and we’re advancing the field through our portfolio of research focused on three areas: Advancing AI, Scaling AI, and Trusting AI.

We’re also working to accelerate AI research through collaboration with like-minded institutions and individuals to push the boundaries of AI faster – for the benefit of industry and society.


POWERING CHANGE WITH AI AND DEEP LEARNING

AI doesn’t stand still. It’s a living, changing entity that powers change throughout every industry across the globe. As it evolves, so do we all. From the visionaries, healers, and navigators to the creators, protectors, and teachers. It’s what drives us today. And what comes next.






Healthcare

ADVANCING MEDICINE AND RESEARCH

McMarvin AI develops and builds deep learning powered tools to help radiologists, radiology departments, imaging centers, and hospitals to improve efficiency, consistency, and accuracy of radiology reporting.

Our mission is to help radiologists detect Cancer, Pneumonia, BMI, Malaria, Skin diseases, Chest X-rays analysis, Bone X-ray Segmentation, Brain tumor Segmentation and many more earlier using deep learning.

Building a Common Platform Across Healthcare, TRANSFORMING HEALTHCARE TO TRANSFORM LIVES.

More Details

AI Cities

DEEP LEARNING FOR SMART CITIES

CREATING SMARTER, SAFER CITIES
Data is the lifeblood of the modern city. Today, it’s being captured by more than 500 million sensors worldwide, and that number is growing exponentially. Video represents one of the richest sensors used, generating massive streams of data that need analysis.

AI is the key to turning this information into insight. It’s transforming how we capture, inspect, and analyze data to impact everything from traffic and parking management to law enforcement and city services. McMarvin Metropolis is leading this AI revolution, giving you the tools, technologies, and expertise to meet every challenge with smarter, faster applications.

More Details

A SAFER WORLD WITH INTELLIGENT INSPECTIONS

INSPECT ELECTRICAL GRIDS & RAILWAY TRACKS

Every year, it takes millions of hours to inspect the millions of kilometres of electrical grids or rail roads for any defect or danger.

McMarvin has developed an #AI solution able to automate these inspections, making our world safer.

We solve the problem of slow inspection, high risk and low assertiveness. This way we bring all the assets into the office and analyze them in just 3 milliseconds.

Artificial Intelligence Platform automatically identifies:
ASSET TYPE, ASSET QUALITY, ASSET ANOMALY, ASSET LOCATION

-

Image Annotation

Intelligent Image Annotation Services

Best Image Annotation & Recognition Service with Pixel Perfection

Mark every image with focused image annotation service to measure the dimension from pixel-to-pixel for annotating every image perfectly. Right tools and technology with precise algorithm is necessary to get the results with highest accuracy. McMarvin specializes in image annotation technology and image annotation deep learning services.

Working with a focused approach and utilizing complex tools and technology, we offer unmatched image annotation services. With tools that work at pixel level, we augmented them using smart algorithms to carry out precise image annotation.

Adept with image processing tools and techniques, we carry out:

Semantic segmentation,
Cuboids, polygons, 2D & 3D bounding boxes
Points and line annotation

Adding great value to business, we start with understanding the nature of the business and then carry out the picture annotation task. Whether you are from fashion, retail, e-commerce or the automobile industry, we ensure your product images are ready for computer vision.

More Details

Object Detection & Tracking

REAL-TIME OBJECT DETECTION

Real-time object detection is the task of doing object detection in real-time with fast inference while maintaining a base level of accuracy.

Humans can easily detect and identify objects present in an image. The human visual system is fast and accurate and can perform complex tasks like identifying multiple objects and detect obstacles with little conscious thought. With the availability of large amounts of data, faster GPUs, and better algorithms, we can now easily train computers to detect and classify multiple objects within an image with high accuracy.


OBJECT LOCALIZATION

An image classification or image recognition model simply detect the probability of an object in an image. In contrast to this, object localization refers to identifying the location of an object in the image. An object localization algorithm will output the coordinates of the location of an object with respect to the image. In computer vision, the most popular way to localize an object in an image is to represent its location with the help of bounding boxes.

-

Text Summarization

Automatic Summarization, Text insights, Redactio, Sanitization and Web crawler for Automated Marketing

Automatic text summarization has played a critical role in helping people obtain key information from increasing huge data with the advantaged development of technology. In the past, few literatures are related to solve the problem of generating titles (short summaries) by using artificial intelligence (AI). The purpose of this study is that we proposed an AI approach for automatic text summarization. We developed an AI text summarization system architecture with three models, namely, statistical model, machine learning model, and deep learning model as well as evaluating the performance of three models. Essay titles and essay abstracts are used to train artificial intelligence deep learning model to generate the candidate titles and evaluated by McMarvin for performance evaluation. The contribution of this paper is that we proposed an AI automatic text summarization system by applying deep learning to generate short summaries from the titles and abstracts of the Web of Science (WOS) database.

Summarization has been and continues to be a hot research topic in the data science arena. While text Summarization algorithms have existed for a while, major advances in natural language processing and deep learning have been made in recent years. Many internet companies are actively publishing research papers on the subject. Salesforce has published various groundbreaking papers presenting state-of-the-art abstractive summarization.

While there is intense activity in the research field, there is less literature available regarding real world applications of AI-driven summarization. One of the challenges with summarization is that it is hard to generalize. For example, summarizing a news article is very different to summarizing a financial earnings report. Certain text features like document length or genre (tech, sports, finance, travel, etc.) make the task of summarization a serious data science problem to solve. For this reason, the way summarization works largely depends on the use case and there is no one-size-fits-all solution.

We at McMarvin currently provides features like Automatic summarization, Text insights, Redaction and Sanitization and Web crawler for automated marketing.

Use Cases:-
1. Media Monitoring
2. Newsletters
3. Internal document work flow
4. Social media marketing
5. Many more NLP based use cases

-

Sports Analytics

McMarvin's SPORTS ANALYTICS

The movie Money ball, among many things, can be considered as the prime example of data-driven performance optimization in sports. AI in sports can provide next-level analytics and has several use cases such as "Scouting and Recruitment", "Training and Performance Analysis", "Maintaining player health and fitness", and "Broadcasting and Advertising".

Our AI models can automatically recognize actions and events in match footage that can reduce the manual efforts for digital broadcasters. With state-of-the-art deep learning algorithms, AI can help in injury monitoring for athletes.

McMarvin AI's sports analytics is built on top of cutting edge technology like computer vision which provides accurate video analytics for coaches/managers to improve the future performances of players.


Use Cases we work on:-
1.Sports Video Summarization
2. Predictive Analytics
3. Injury Analysis
4. Player Tracker
5. Fans Engagement

-

Smart Parking

Car Parking Occupancy Detection Using Smart Camera Networks and Deep Learning

Computer vision is used to detect empty parking spaces. As the spaces become available it will be assigned to a waiting car who will then be directed to the spot.

-

POTHOLES DETECTION

MACHINE LEARNING BASED APPROACH FOR POTHOLE DETECTION

Potholes, often caused by water, is the nuisance which often results in vehicle damage, passenger discomfort, and accidents. The volume of traffic and the axle load experienced by the road are example factors that lead to fatiguing of the road surface, resulting in the formation of cracks. These cracks allow water to seep through and mix with the asphalt and concrete. When a vehicle drives over this area, this water will be expelled through the crack with some of the asphalt, and this will slowly create a cavity underneath the crack. Eventually the road surface will collapse into the cavity, resulting in a visible pothole.

-

Optimize Every Plant

MAKE EVERY PLANT COUNT

Using computer vision and artificial intelligence, our smart machines can detect, identify, and make management decisions about every single plant in the field.

Crop protection is just the beginning. Stay informed with our latest developments.


AUTOMATIC IMAGE RECOGNITION FOR PLANT DAMAGES
Every plant disease, pest, or nutrient deficiency leaves a specific pattern to which our software quickly learns to detect with up to 95% accuracy.

OUR SOLUTIONS

McPlant
An easy plant disease diagnostic & monitoring tool With our software, we can provide customized solutions for every need.
McPlant- our simple plant disease diagnostic & monitoring tool

SURVEILLANCE SYSTEMS
Surveillance systems for Indoor Farming & Greenhouses.
Automatize plant protection control in your greenhouses! Sit back, relax, and control plant protection in real-time if your plants are suffering from any deficiency, upcoming pest or disease. Minimize worries and inputs, maximize security and outputs – with McMarvin’s image recognition solution!

Cheap and autonomous cameras send pictures of your plants and you will get the results on your device right away. McMarvin’s technology bring a true expert into your greenhouses, that never sleeps and never leaves. Putting the safety of your harvest in YOUR hands

-

PROTECTING ENDANGERED SPECIES

Our challenge is how to harness artificial intelligence to create an environment where there’s room for us, and all species in this world.

THE MORE WE CAN STUDY THEIR BEHAVIOR, THE MORE WE CAN HELP TO PROTECT THEM – AND SUSTAIN THE EARTH'S BIODIVERSITY THAT SUPPORTS US ALL.

→ FOOTPRINT PATTERN ANALYSIS
→ BEHAVIOUR ANALYSIS
→ TRACKING AND MONITORING

Their tracks tell a collective story that holds incredible value in conservation.

WHERE ARE THEY GOING? HOW MANY ARE LEFT? THERE IS MUCH TO BE LEARNED BY MONITORING FOOTPRINTS OF ENDANGERED SPECIES.
Artificial intelligence help us recreate some of the skills used by indigenous trackers.

WILDTRACK RESEARCHES ARE EXPLORING THE VALUE AI CAN BRING TO CONSERVATION
AI solutions are designed to enhance human efforts – not replace them. With deep learning, given enough data, a computer can be trained to perform human-like tasks such as identifying footprint images and recognizing patterns in a similar way to indigenous trackers - but with the added ability to apply these concepts at a much larger scale and more rapid pace. Analytics really underpins the whole thing, potentially giving insights into species populations that WildTrack never had before.

-

Driver safety system

ALERTING DISTRACTED DRIVERS

The new standard for fleet safety is here.
Stop Collisions at the source.
McMarvin is purpose-built to help commercial fleets and drivers prevent collisions at the source: distracted driving.

Increase productivity.
Help your drivers focus on the road ahead, and keep your vehicles active and productive.

Reduce losses and costs.
Help drivers avoid collisions, near-misses, and traffic violations to reduce losses and lower costs.

Real-Time Prevention.
Help prevent collisions before they occur with the industry's only automated real-time alerts built with drivers in mind:

Distracted Driving
Tailgating
High Risk Warnings

-

Video Analytics

Keep an eye on everything and get reports & alerts.

Develop automatically analyzing video content to detect hidden patterns and activities.

Video analytics has become a new way to analyze data that has no user interactions with the systems. It has new ways to detect hidden patterns, behavior, or incidents to make smarter and wise decisions. Video analytics has given a modern form of exploring activities that otherwise are very difficult to trace. It has gained popularity in application and business which has tremendous user walkins and personal interaction.

Video analytic key aspects

Motion Detection
One of the most common detections and the challenge is detecting movement. This detection helps in every aspect, like securing the premises and identifying speed. The camera that has image sensors and is using light & dark pattern can identify motions. While analyzing, data sets are trained to determine movement, and that way near to real-time detection can be detected and analyzed.

Facial Recognition This is the best technique for identification. Mostly used for security and crime control. However, now a variety of other ways can be explored using this. Phone unlocking, helping differently-abled people using facial recognition, and attendance.

Object Detection and Tracking Systems can be made smarter to understand objects in the camera frame and track them over some time. This helps to locate items in the mall and objects in the warehouse. Different and innovative use cases are revolving around this.

Gesture identification This has gained prominence in the sports field. Players’ gameplay is recorded and analyzed. This analysis is used to improve gameplay. Apart from sports, other areas are exploring it and gaining popularity.

Sentiment identification This is a combination of tracing user’s activity along with other personal details to analyze and understand the behavior and patterns of the user’s mind. This is becoming highly popular as it can influence a mass towards a common goal.

Industry-wise Video Analytics benefits

Outdoor Advertising and marketing It's hard right now to capture the analysis of several views for outdoor advertisement. Video analytics can come to aid for this difficulty.

Parking infrastructure Systematic identification of parking space can be handled using Video analysis. It helps in infrastructure planning.

Banking and security Face detection, anomaly activities, etc. can be identified at banks and ATMs.

Retail counters or window shoppings Improve business by observing the user’s behavior.

Games and Sports Training or coaching of athletes, improving their skills, planning strategies, and reducing their injury on the field.

Education sector Increase the level of education and make it easy for students to understand.

Government and Law Identification of suspicious activities in the given premises. Monitoring of law adhering.

Health/rehabilitation centers Video analysis provides the ability to monitor and track improvements in patients.

More Details