Automotive Digitization Automation 

European automotive market differs from north american, and in France in particular limitations to online payments, credit card authorizations and legal details before being able to put a vehicle on the road restrain fully automated car vending machine or online second hand vehicle retailers such as the famous CARVANA. 

That being said, the digital era requirements to bring the customer to your shop instead of another are equally challenging : in less than ten years, the amount of prospects went from at least 3 to 4 visits before buying a used car to less than 1. Long story shot : the prospect has chosen it's vehicle online before going to the retailer. This is where user experience and product description exhaustivity make the whole difference.

At the core of the concept the idea is to bring the 360° experience that many customers already know in product such as Google Street View (Navigation) and Matterport (Real Estate) to any vehicle online product sheet. This should be performed without the costly and time-consuming need for a video production or digital marketing agency, but instead the workflow would be enabled in-house or via 3rd party on-the-go contractors using affordable and reliable devices to execute the digitization process, and a smooth and scalable Digital Assets Management Software to manage the quality assessment and publishing.

First proof-of-concept took 6 months to deliver, consisting of an improved version of Ajaris Orkis System DAM software with ability to handle complex assets composed by a multitude of picture assets in addition to state of the art web-friendly player easy to embed in customers websites. This went with plans and guidelines for building or improving remote controlled vehicule photobooths easily embeddable in a processing factory or a warehouse, using the opensource APIs for Canon Cameras and cinema lighting techniques. To speed up the process we included some heavy duty robotic platforms able to lift and rotate vehicle up to 3.5t, All wrapped in a user friendly interface with automatic correction of lighting, white balance and focus for easy maintenance. 

After the succesful delivery of the 1st main iterations, levers of improvement emerged that allowed to split the concept into a scalable solution, which eventually has been forked into a Mobile App Based Solution and a Heavy Duty Improved Photobooth, available in two sizes for motorbikes up to minivans.

A full digitization workflow takes 8 minutes and can be performed both locally inside dedicated studios or "on-the-field" with a pocket camera and a mobile device, allowing high productivity in every context. 

No extra knowledge of photography technique is required : the agent is driven by the app along the full process which is designed to remain simple and friendly.

Concept has succesfully been extended to a various range of industrial customers, from STVA (Automotive Railway Logistics Network) to Aramis Auto (one French leader of 2nd Hand automotive processing) and Dubreuil Group (the very 1st french fully automated digitization photobooth proof of concept).

AI Workflows for Powerful Food Photography

Guapa Juice is a belgian brand specializing in delivering minute made fresh mixed fruit juices, sweets and milk shakes in mall food courts and other strategic stores. From Brussels to Leuven, the brand capitalizes on a dynamic and succesful startup reputation which transcribes into its communication.

For a food photographer, creating pop effect via motion is highly technical and involves both a perfect knowledge of lighting techniques at high speed to freeze droplets and liquids movements in a splash and perfect timing to catch the point of contact of fresh food chunks with the dish or - in this case - the cup and it's content. Considering the number of receipes available in Guapa Juice Catalog the amount of shots to get a perfectly and consistent series of splashes while shooting all kinds of fruit and vegetables chunks into accurately textured and colored juices require a HUGE amount of trials and errors. Hence the cleaning of the studio and overall waste of food due to many attempts needed to catch the perfect composition for each receipe... And quite some luck.

Considering the amount of defects and uncertainty of the production process of a full catalog of "liquid explosions" based on a traditional workflow, we decided to bring in the experimental Artificial Intelligence Workflows based on available litterature on this topic by March 2023.

The client actually shortened up the moodboarding process and instead came with a specific - and already sketched - idea of the final expected rendering. This helped the research and development phase but allowing to cut right through to unknown and go for the workflow constraints. 

Three tools have been shortlisted to handle the process : first of all using Midjourney AI on Discord Version as it appeared to be the most consistent and reliablecreative iteration tool of it's time, but with the following limitations (obsolete by now) of delivering only low resolution assets (less than 2 megapixels) and not (yet) allowing local adjustments on each iteration. 

To properly nurture the learning curve of the AI a pro license was required, allowing to reset and sharpen at will the learning curve of the AI model, based on actual primary sets of photos physically made in our studio in Brussels. Two sets of pictures were therefore combined : a first one destined to teach the model what type of assets we expect while describing objects such as "pineapple slice", "banana chunk" or "little carrot with leaves". Then we produced a second set of pictures picturing the juice cup with the actual receipes combinations around it.

Finally a third bunch of pictures were made specifically to explain to the model how the container (paper cup) would be cutted to reveal the inner mix and showcase the client logo in a clean and consistent framing.

Then the iterations began (600 on average) to create a consistent art direction into the model for each receipe. The validated outputs were then upscaled to 12 megapixels using Topaz Gigapixel AI allowing a high quality postprocessing using Adobe Neural Engine and Adobe Photoshop Ai Assistants for local corrections (now called Firefly).

At Delivery, all assets are downscaled to 2Mpx again and compressed to optimize loading time and smooth experience using the touchscreen devices.

From brief to Production Delivery the actual full process took places in matter of weeks instead of months - and avoided a significant amount of studio cleaning and potato-tube launcher reloading, even if it sounds funny it can become a real assistant killer when reproduced hundreds, if not thousands of times. Along the full process this included more "traditional" operations for packshot photography workflows such as processing branded shiny metal camping bottles, extra cup sizes, side dishes and other color variations based on a simple but important pre-production step consisting of measuring the color and density of each mix and creating a trustworthy reference palette.

In fine, even if the full process seemed to took the same amount of energy as if it had been produced in a more conventional way, it's effectiveness and the ability to generate new assets almost immediately worth the price of the effort. For the future, this kind of workflows may be even more improved by using cycle of iterations assisted at other steps such as the prompting (involving GPT-4) and the opportunity to animate the results (such as custom workflows available in Runway AI).

In 2024, geographic data has become an indispensable tool across various industries, revolutionizing how we interact with the physical world. From the press to archaeology, public infrastructure, museography, and cultural mediation, the applications of geographical data are vast and ever-evolving. This article delves into the significance of geographic data, the advancements in data gathering technologies, and the implications of its use, highlighting the crucial role of Geographic Information Systems (GIS) and Digital Assets Management (DAM) systems in shaping our future.

• Press: In journalism, geographic data aids in visual storytelling, helping to contextualize news events. Reporters use it to analyze and communicate complex stories, such as climate change via meaningful dataviz or political conflicts, with a spatial dimension. Journalists use advanced digital assistants to dive into an increasing amount of information and live camera feeds from the field, allowing to dig into asset clouds by location along the crew journey.

• Archaeology: Archaeologists leverage geographic data for site discovery and excavation planning. Technologies like LiDAR and photogrammetry reveal hidden structures and landscapes, transforming our understanding of historical sites. This reveals a new challenge for digital conservation as the diversity of encoding standards quickly expanded. Some platforms aim to harmonize the storage and display such as sketchfab. The interesting point is here the convergence between classical survey operations and object digitization into common interfaces and aggregated tools for quick sharing and commenting.

• Public Infrastructure: In public infrastructure projects, geographic data ensures efficient planning and management. It helps in routing, zoning, and environmental impact assessment, leading to more sustainable development. It is no surprise that historical partners of survey operations such as Faro and Autocad quickly became leaders in providing integrated solutions.

• Museography and Cultural Mediation: Museums use geographic data to trace the origins of artifacts and create immersive, interactive exhibits. This technology bridges the gap between historical artifacts and modern audiences, enhancing educational experiences. Lascaux VR by Dassault systems has been a vibrant showcase for the mediation technologies as per La Cité du Volcan in Réunion Island.

...not mentionning the usual driving assistants and itinerary calculators, and other tools so oftenly used we take it for granted. 

Completing the historical toolbox : survey mapping, aerial photography, bathymetry and satellite imagery, already highly contributing the strategic sector of geointelligence, are new incomers coming for a extended range of industries such as smartphone manufacturers, cinema providers and entertainment.

• LiDAR Technology: Light Detection and Ranging (LiDAR) has become more affordable and accessible, providing detailed 3D models of physical environments. Its precision is invaluable in industries like archaeology and urban planning.

• Drone Technology: Drones have revolutionized data collection, offering a bird's-eye view of landscapes. They are crucial in mapping, agriculture, and environmental monitoring.

• Photogrammetry: This technique, involving photographs from different angles, creates detailed maps and models. It's widely used in museography for artifact reconstruction.

Surfing the wave of the thriving geodata ecosystem a number of new actors also emerge such as Prométhée New Space.

• Nvidia's Contribution: Nvidia, a leading GPU manufacturer, has propelled the processing capabilities for geographic data. Their hardware supports complex computations required for analyzing vast amounts of spatial data. Boosted by the power of big data, the sector now also count with new extrusion capabilities from 2D source images based on a rising community of developpers working on depth AI analysis.

• Epic Games and Reality Capture: Epic Games, known for its acquisition of Reality Capture software, has brought photogrammetry to the forefront, aiding in creating realistic environments in gaming and film industries with low cost equipment on top of dedicated solutions such as Matterport, widely used in museography and Real Estate, and Leica BLK GeoSystems well known by most of Architecture Specialists.

• Leaking Sensitive Information: The inclusion of geographic data in public releases, like social media posts, can inadvertently expose high-value assets or strategic locations, posing security risks.

• Threat to Natural Resources: Revealing the locations of endangered species or sensitive ecosystems can lead to exploitation and harm, emphasizing the need for responsible data sharing.

Benefits :

• Cross-Platform Development: Integrating GIS with Digital Assets Management systems is crucial for cross-platform developments. This synergy enables efficient management and utilization of geographic data across different media.

• AI-Assisted Governance and Automation: The future beckons the use of AI in geographical data governance. AI can automate workflows, enhance data accuracy, and offer predictive analytics, paving the way for smarter decision-making.

As we advance in 2024, the integration of geographic data in various industries highlights its undeniable value. However, with great power comes great responsibility. The blend of Geographic Information Systems and Digital Assets Management systems emerges as a critical solution. This integration, coupled with AI, will not only streamline data management but also ensure ethical and efficient use of geographic information. The future of geographic data is not just about technological advancement; it's about harnessing these tools for sustainable and responsible growth across all sectors.