Video and Image AnalyticsVideo and Image Analytics
PixL analytics leverage cutting-edge machine learning techniques---
FACE DETECTION AND RECOGNITION
PixL uses state-of-the-art deep learning algorithms to detect and recognize faces in unconstrained conditions including non-frontal faces. For each detected face, the module uses a deep neural network to extract a low dimensionality facial feature vector that is discriminative of the face and performs clustering to group similar faces. A tracker is integrated with face detection to correlate continuous occurrences of faces in the video. Tracks of similar faces are grouped into a single entity and analysts can use the analytics drill down pages or the video player to navigate through the detections and tracks.
OBJECT DETECTION AND TRACKING
PixL uses advanced artificial intelligence and machine learning models to detect categories of objects. The object detection modules are combined with a tracker to detect and predict the positions of the objects. The tracker adaptively learns and updates the appearance of an object using a discriminative learning method to distinguishing between the object and the surrounding environment. This results in persistent tracking that is robust to natural image changes and occlusion. Tracks of similar objects are grouped into a single entity and analysts can use the analytics drill down pages or the video player to navigate through the detections and tracks.
For intelligence and surveillance applications, PixL's co-occurrence analytics can identify when and where the tracks of entities overlap in a video. For each overlap, or co-occurrence, details of the time of overlap, frame IDs, duration of overlap, number of overlaps, and details of overlapping faces are provided. These analytics provide the capability to identify two or more people who appear in the same scene and other scenes in which the same individuals are seen together. PixL’s interactive user interface allows the analyst to search through co-occurrences and view the frames associated with each co-occurrence, giving context to the instance of each overlapping track.
PixL's face recognition analytics allow analysts to recognize individuals of interest by matching faces detected within a video or set of images against a user-provided database of faces. PixL performs off-line analysis using deep learning of the user-provided images to extract user-specific feature vectors and compares them against faces detected in the video. For commercial use cases, PixL comes pre-configured with a celebrity dataset for celebrity recognition. The celebrity dataset includes over half a million images of 50,000 celebrities. PixL provides analysts with the tools needed to update, label, and maintain their own custom image/face datasets against which face recognition can be performed.
SATELLITE IMAGERY ANALYTICS
To address issues related to low resolution data and the overhead camera angle, PixL Satellite Object Detection Analytics leverage specially trained machine learning models to identify objects of interest in satellite imagery. These analytics include a deep learning-based model that was trained using a satellite image dataset containing millions of labelled objects. The model predicts the positions of bounding boxes, the object classes, and their probabilities. A tracker is integrated with satellite object detection to correlate continuous occurrences of objects in the video. Tracks of similar objects are grouped into a single entity and analysts can use the analytics drill down pages or the video player to navigate through the detections and tracks.
Other FeaturesOther Features
In addition to a suite of analytics, the PixL dashboard includes a rich set of tools to view videos, explore the analysis, share, and export results. Some examples of these tools and features include:---
PIXL VIDEO PLAYER
Enables analysts to view the original and fully analyzed video with bounding boxes and annotations. PixL's video player can enhance viewing capabilities with controls for zooming, panning, saturation, and hue.
PixL’s interactive track data search capability allows analysts to explore the analytics result using text and Boolean-based search rules and grammar. For example, analysts can execute queries such as “Face_id:1 AND overlaps:2” to find all instances where a particular face overlapped with two or more other faces.
SHARE AND EXPORT
PixL’s export feature makes it easy to share your analysis results and reports with your peers. Reports can be emailed to other users, making knowledge sharing an efficient process.
For enterprises interested in using PixL analytics with their proprietary data sets and data feeds, and maintaining the installation behind their corporate firewall, we offer an option for on-premise installation and deployment of the PixL analytics engine. All analytics components have been containerized and prepared for scalable deployments on GPU machines. Our engineering team will work with you to understand your requirements and data sets, recommend the appropriate hardware configuration, and install PixL analytics engines, analytics models, visualization dashboard, and user management tools to meet your enterprise’s analytics needs.
Don't Take Our Word for ItDon't Take Our Word for It
Industry experts weigh in---
If you need to make sense of all the noise on social media you need to use Scraawl! Want to build a community or identify true influencers for your business, you need to look no further than Scraawl. I'm amazed by how quickly you can find relevant information and users by digging into many layers of conversations and putting into usable information and reporting.
Adel de Meyer
Social Media Influencer
Scraawl is the only platform that you need for all of your social media analytics needs. It includes an impressive suite of tools: dashboards, heat maps, customizable workflows, graph analytics, network analysis, and metrics to track social mentions, connections, influencers, sentiment, communities, timelines, and more. Scraawl's cloud-based analytics proves that it is the one tool to rule them all: SMAC (Social, Mobile, Analytics, Cloud).
Principal Data Scientist at Booz Allen Hamilton
Our team has been teaching social media courses for 3 years and in the process have trained over three hundred professionals and have evaluated over 50 different social media analytic tools. Scraawl is the most stable and reliable tool we've used in training and with the abundance of easy to use analytics, it is no surprise that class after class, our students pick Scraawl as their tool of choice.
CEO - Echo Analytics Group
As social media analytics continues to evolve, technology tools will be more vital than ever to better understand the gazillion numbers of data. Scraawl gave me the ability to paint the story around our brand and where we stand against our competitors [...] The best thing about Scraawl though is it’s cutting-edge data visualization analytics and how to turn those into actionable insights...
Founder of Global Social Media Marketing
Using Scraawl we were able to solve our social media questions quickly and easily. Scraawl’s unique analytics as a service puts data science into everyone’s hands. With a few clicks of the mouse, Scraawl converts social media information into knowledge, that is actionable, easy to understand and engaging.
Kant Consulting Group
Scraawl made tracking my event engagement effortless. I was able to run campaigns and track engagement without the hassle of setting up new technology. It was just a few clicks and we were up and running. I'm not sure what I would have done without this app.
Social Media Influencer