Northeastern University

<p>Northeastern University’s Center for Research Innovation (CRI) is an impact driven initiative bridging the gap between laboratory research and need-based solutions. The CRI serves as the University-wide portal between industry and leading-edge innovations from Northeastern’s use-inspired research portfolio.</p>
<p>Over the past seven years, research activity at Northeastern has more than doubled. Northeastern’s cutting edge faculty focus their use-inspired research on solving the nation’s greatest challenges in health, security, and sustainability. The Center for Research Innovation connects private companies with the researchers and inventions that meet their business needs – now and in the rapidly evolving future. Our team of professionals all have business and entrepreneurial experience. We strive for a high level of responsiveness and service, moving with speed and flexibility.</p>
<p><strong>Industry Connections:</strong></p>
<p>The CRI is the University’s bridge to industry. We are continuously building relationships with companies to identify their key technology needs and to explore opportunities for collaboration. Our network spans across industry, from the Life Sciences to the Physical Sciences. The CRI aims not only to license individual technologies, but to form long standing partnerships with industry, leveraging the core competencies of our faculty and students.</p>
<p><strong>Collaboration Benefits:</strong></p>
<p>The CRI aims to move beyond the standard paradigm of one-off licenses, focusing instead on forming long-term relationships with industry. We look to assist companies with their ongoing technology needs, leveraging the expertise of our faculty. Collaborating partners can expect flexible terms and IP policy, “high touch” and responsive service, world leading research and development and access to Northeastern resources, including use of labs and equipment.</p>
<p><strong>Research Capabilities:</strong></p>
<p>Northeastern has cutting-edge research in areas such as the Life Sciences, Nanotechnology and Network Research. The CRI can arrange briefings from faculty whose research aligns with your key corporate priorities.</p>
<p>The CRI team is agile and responsive – focused on the translation of University innovations into tangible solutions through licenses, spinouts and collaborations. Our dedication to establishing ongoing dialogue with industry informs Northeastern’s progressive research, enabling a productive balance between exploration and implementation.</p>


<h1 id="background">Background</h1>
<p>Over the past several years, there has been a large shift towards telemedicine, digital health and in-home fitness. The pandemic has only helped to accelerate this change in our approach away from in-person healthcare and exercise. Artificial intelligence plays a critical role in enabling technologies in these fields. One such technology is Pose Estimation, a computer vision task using a machine learning model to estimate the pose of a person from an image or video by estimating the special locations of key body joints. Pose estimation requires high computational resources which has limited the range of applications where it can be used. Traditionally, pose estimation is conducted via a graphical model. Recently, developments in deep Convolutional Neural Networks (CNN) have significantly boosted performance. Many researchers tend to use a deep and high-capacity CNN architecture pre-trained on large-scale datasets, and adapt it to the pose estimation task. However, the scaling problem still remains as a bottleneck. One popular solution is to seek a large capacity network as the backbone to learn better feature representations. Nevertheless, the model complexity of the large backbone architectures, in terms of time and space, makes it hard for direct applications on mobile and embedded devices. Therefore, there is a need to design customized light-weight CNN modules to reduce the computational cost and storage size for further on-device applications.</p>
<h1 id="technology-overview">Technology Overview</h1>
<p>Northeastern spinout, AInnovation, has invented a comprehensive artificial intelligence framework through novel light-weight deep learning techniques of quantitatively visual sensing, analyzing, understanding, and modulating human behaviors through low-cost and portable computer vision devices, such as smartphones and tablets. This framework enables complex computer vision programs, including human pose tracking, behavioral recognition, and motion capturing, to run on platforms constrained by limited hardware, bringing cutting-edge innovation to telemedicine, remote rehab, virtual-first care and in-home fitness.</p>
<p>Most existing light-weight model compression technology, has been focusing on the lower level or hardware level implementations, e.g. pruning, quantization or knowledge distillation. Such methods are generic and not application oriented, which may suffer considerable degrading of algorithm accuracy, and unpredictably fail in many cross-domain scenarios. In contrast, AInnovation has invented a customized AI model compression technology which is application oriented. The model design is implemented on the model components level, which is more robust and can achieve superior accuracy enhancement and model size reduction.</p>
<h1 id="benefits">Benefits</h1>
<ul>
<li>Superior accuracy and robust pose estimation.</li>
<li>Computationally less expensive compared to the other pose estimation methods</li>
<li>Can run on resource constrained devices such as smart phones and tablets</li>
</ul>
<h1 id="applications">Applications</h1>
<ul>
<li>Telemedicine &amp; remote physiotherapy</li>
<li>In-home fitness</li>
<li>Gaming</li>
<li>Security/defense</li>
<li>E-learning/remote education</li>
<li>Any industry that requires an AI-based solution</li>
</ul>
<h1 id="opportunity">Opportunity</h1>
<ul>
<li>Partnering for customized solutions</li>
<li>Identifying new space for company</li>
</ul>
