For years, I’ve watched IT data integration teams wrestle with the same outdated methods for setting up shipment status interfaces, only to be met with lackluster results. The truth is, traditional data integration methods are labor-intensive and time-consuming. Worst, and foremost, they’re also prone to errors and ambiguities that throw entire supply chains off track. It’s time to admit it: there’s got to be a better way to achieve seamless shipment tracking in our supply chains.

In this article, I’ll introduce you to the innovative world of Computer Vision AI and show you how it can revolutionize your shipment tracking. First, I’ll explain how this technology can enable end-to-end visibility across your supply chain. Then, I’ll share some compelling examples of how image-based digital integrations can provide more accurate and timely updates on shipment status events. Specific tracking examples include shipped, intransit, delivery and shipment exceptions.

End-to-End Shipment Tracking Using Computer Vision AI: How It Works.

To me, computer vision AI represents a paradigm shift in traditional end-to-end shipment tracking. With image-based tracking, supply chains can leverage the inherent understandability of the images themselves and save the trouble of sharing bulky, error-prone, data-translated transmissions. 

Just think of the possibilities when a shipment image is paired with only essential contextual data such as GPS location, tracking IDs, and timestamp. Indeed, a shipment status message becomes much more universally comprehensible than current proprietary shipment status data formats. Hence, this image-based approach of transmitting shipment statuses sidesteps most data interoperability hurdles that plague other tracking solutions. To illustrate, below is a 5-step process on how an imaged-based shipment tracking solution can provide unprecedented end-to-end visibility to supply chains. 

A Computer Vision AI Solution for Image-Based Shipment Visibility

1. Localized Camera System Captures Image or Video of Tracking Event. This includes image, tracking ID, local time, and GPS coordinate.
2. Image-Based Shipment Status Event Transmitted. Then, the local system sends raw digital data to a centralized AI shipment tracking translator.
3. AI Interprets Image for Tracking. An AI Machine Learning (ML) translator Interprets raw tracking data into an actionable shipment status.
4. Shipment Status Message Shared. Then, the AI translator shares shipment status messages with stakeholder systems.
5. End-to-End Shipment Visibility. As a result, decision-makers and their systems have trusted, real-world status of shipments – a Single-Source-Of-Truth (SSOT).

For a more detailed explanation of how image-based tracking can work, see my article, How to Make End-to-End Shipment Tracking the Best Using Computer Vision AI.

Examples of Image-Based Shipment Tracking Events: Shipped, Intransit, Delivery, Exceptions.

Without a doubt, image-based tracking is a much better way to exchange shipment status. Indeed, current data integration methods are time-consuming to set up, resulting in bulky, error-prone data translation interfaces. Below, I’ll provide specific examples of where advanced computer vision AI technology has the capability to generate shipment status across the supply chain. This includes shipping, receiving, intransit, delivery, and shipment exceptions.

1. Shipping / Receiving Shipment Tracking Events: Leverage Computer Vision AI to Validate what is Shipped or Received at the Warehouse

At the warehouse, computer vision AI can be used to validate shipments by comparing the items being shipped or received against the orders or manifests. For instance, a forklift operator loads pallets of goods onto a truck. As the truck is loaded, a computer vision AI camera at the dock door tracks the pallets. Further, the system confirms the shipment matches the expected items and quantities. Also in another example, a distribution center can use the same AI system during the receiving process. For instance, it can verify receiving packages against the expected shipment, flagging any discrepancies. In both cases, the AI system uses OCR and barcode scanning tech to “read” the image or video. 

Moreover, to minimize supply chain data integration challenges, the imaging system at the dock door does not necessarily need to “translate” the image locally. Indeed, the local camera system at the shipment’s location can instead directly transmit images and GPS locations to an overall supply chain visibility system or partner systems. From there other systems can use an AI computer vision module to “translate” the image into meta-data in the form of a shipment status event. For an example of a standalone computer vision AI system for dock-door use cases, See  Kargo‘s solution. Here, they offer imaging towers installed on either side of the loading dock doors.

2. Intransit Events: Verify Shipments Arrived or Departed No Matter What the Mode of Transportation

For intransit events, supply chains and their logistics partners can place computer vision AI cameras and sensors at key locations along transportation lanes. For instance with rail, the local operation places cameras in train terminals to capture images of rail cars. Thus, these cameras confirm a shipment’s arrival or departure. Also, this use case holds true for trucks carrying goods that pass through a toll booth or receiving gate. Here the cameras take snapshots of the truck and its license plate, tracking the shipment’s movement. This can even work for ocean ports where cameras take pictures of ships arriving at an assigned berth. Also, cameras can take snapshots of cranes loading and unloading containers. 

Again in the case of intransit events, a standalone AI system can “translate” the image or, better yet, the local operator can transmit the image with GPS locations to supply chain partners. Then partner systems can use AI image recognition to convert the image to metadata and then into a shipment status event. This in turn, results in a reliable shipment status event for each stakeholder. Additionally, this image exchange approach simplifies costly data integration. For example, see Genlogs‘ Freight Intelligence solution leveraging an image-based sensor network.

3. Parcel Delivery Event: Certify that the Package Was Delivered to the Right Place, On-Time

Upon delivery, image-based tracking can certify that packages were delivered to the correct location and on time. To illustrate, an ecommerce delivery driver drops off a package at a customer’s doorstep. Here, a parcel carrier has the computer vision AI integrated into the driver’s handheld device or even Augmented Reality (AR) glasses. Then the system can automatically confirm that the driver delivered the package to the correct location. This can also work with AI-powered parcel delivery lockers or mail rooms. Here, the computer vision tech verifies the package was placed in the correct locker and records the time of delivery.

4. Shipping Exceptions: Determine that Exceptions Have Occurred or About to Occur

Here, computer vision AI can enable operations to proactively detect damage during transit, incorrect routing, or delays. To illustrate, image-based tracking can monitor video footage of a warehouse receiving dock. In this case, it looks for damages to boxes or products. If detected, it sends an alert to operations for action. Another example is where cameras at a port take a picture of a shipment that is damaged or tampered with. Also, a local operation could use computer vision AI with geo-fencing to generate an alert if a shipment left a restricted area.

Again, there are two ways that the computer vision AI system could work in generating shipment exception messages. First, a standalone AI system triggers a shipment exception alert. Also, a second option is where the on-site system could just transmit the image with the GPS location to stakeholders’ visibility systems. Then, these systems could “translate” the image and GPS location into a shipment status exception event. Also, another benefit of these AI systems is that supply chains could use these images with GPS and local timestamps to estimate if a shipment is on-time or delayed.

More References.

• Picture-Perfect Tech for Supply Chain Visibility: The Use Of Emerging Computer Vision AI To Find Out What Happened
• Computer Vision AI: The Unlimited Ways To Use This Awesome Tech To Empower Supply Chains
• How to Make End-to-End Shipment Tracking the Best Using Computer Vision AI

Picture-Perfect Tech for Supply Chain Visibility: The Use Of Emerging Computer Vision AI To Find Out What Happened

Need help with an innovative solution to make your supply chain systems work together? I’m Randy McClure, and I’ve spent many years solving data interoperability and visibility problems. As a supply chain tech advisor, I’ve implemented hundreds of successful projects across all transportation modes, working with the data of thousands of shippers, carriers, and 3rd party logistics (3PL) providers. I specialize in ?proof-of-concept and operational pilot projects for emerging technologies. If you’re ready to modernize your data infrastructure or if you are a solution provider, let’s talk. To reach me, click here to access my contact form or you can find me on LinkedIn.

For more from SC Tech Insights, see the latest articles on Information Technology, Shipping, and Interoperability.