HOME / CASES / Logistics center

CVC neural network video analytics implementation in a logistics center case

How to transfer the warehouse logistics center operations to a fundamentally different level of management control in six months
In this case, the customer was a major company in the segment of electronic commerce. Due to the terms of the contract, we cannot disclose the name of this company, as well as the economic indicators "before" and "after" the CVC implementation. However, in the course of the project there were made a lot of discoveries and interesting conclusions about what is important to consider when implementing neural network video analytics in this particular business area. Some nuances are so important for those whose activities are related to warehouse logistics that we want to share them on our website.

Note that the client turned not only to us, but also to two other well-known contractors on the market, who were also presented with the terms of reference for the study and preparation of the estimate. The first company refused because of the complexity of the terms of reference. The second company quoted a price 10 times higher than our proposal... But even without this information, we understand that there are simply no offers on the market for video analytics with an out-of-the-box product that can compete with ours at the moment.
Contents list

Pilot project launch

Representatives of the customer came to us independently thanks to a simple search query "warehouse video analytics".
It is extremely important for us that even before making a decision to work together, the client understands the specifics of our offer
Usually all of our customers study the site quite carefully before they leave a request. So we tried to make the site as informative as possible, paying attention to how we implement neural network video analytics and neural network robots in different industries. At the same time we are not putting advertising cartoon clips on our site, but concrete videos from objects, thanks to which it is clear how our neural network can see and what results we get.
On the client's side, the development department interacted with us on this case. The department consisted of core employees from various services of the company, including logistics. The task of these employees was to voice the potential problems of their departments. After that, the department's specialists were responsible for implementing the developed technology, implementing pilot projects, and, as a result, confirming that the chosen technology was capable of localizing or completely eliminating such pains.

The pilot project was launched at a site with the following characteristics:
  • number of cameras: 2,400 pcs;
  • number of gates for receiving shipments: 120 pcs.

    What tasks CVC had to solve and why our competitors were afraid to take on this project

    The range of tasks that needed to be solved for this case was really wide. So the first thing we started with was to divide all the tasks into groups.

    Group 1. Robotic control of the shipment acceptance process

    The neural network robots had to determine exactly how many places were loaded into a particular vehicle, compare the data to the accounting system and identify deviations.
      The first feature of the task
      - The presence of "reverse unloading" at the site
        Imagine a situation: a car with 20 pallets has driven into a facility. However, the warehouse only needs 15. At the same time the first 5 are blocking the unloading of the required 15... This is not terrible at all, just forced to unload the first 5 places to free up the possibility of unloading the next 15.

        But at this point, the following can happen: not all 5 unloaded back or unloaded back 6 of 5, grabbing something extra. These mistakes can be made without malice, but in the case of "manual" control there is a need to search for hours for this or that shipment. And it really can take hours, because the operator has to personally watch numerous videos, not knowing where and how to look for a lost pallet. And given the number of cameras and gates on the site, such a small task can take from several hours to several days.

        The task of the robots in this case was not to prevent an error, but to promptly report at which gate and with which machine an incorrect backload occurred. This way the search for the load took not days, but seconds, as the robot instantly showed a video of the failure: what had been loaded incorrectly and where it had gone.
          When the customer assigned us this task, he had a separate task block for the delivery and a separate one for the unloading. For us there is no difference in these processes, and we can solve two global customer issues with a single solution.

          For neural network robots, the processes of delivery (goods enter the object) and unloading (goods leave the object) are identical from the point of view of the logistics object.
          The second feature of the task.
          - Specific accounting systems with which to compare the data obtained

            The problem appeared in situations where goods were being prepared for packaging. We were required to connect all these processes with the customer's various video surveillance systems.

            In addition to the specificity of the accounting systems themselves, it is important that these systems were not one, not two or even three. Note that this is quite normal for a company that performs complicated logistics and complex processes. We would venture to guess that this was the main problem that other contractors could not handle. As a result, they inflated the price tag, and some even abandoned the project.

            Note that in the warehouse, as a rule, there is already some kind of video surveillance system (what kind, for us, does not matter). In the case of this customer there was everything at once and in different parts. Different processes have different types of equipment and different types of software that work with these videos. The task for our system was to instantly (on demand) demonstrate the whole path of the goods within the logistics facility.
              CVC program is able to work simultaneously with different accounting systems, including the "unfriendly" for the unloading of data and docking with them. This allows us to quickly enough to offer working solutions for our customers.
              As a result, if a customer informs us that a product has been crushed, it is easy for our customer to find out where this problem with the product occurred.

              This will not require, as before, to manually enter each system and look for that product at different points in time in the archive of video recordings. Now it is enough to enter the box number or pallet number (any entity that exists in the warehouse) and get instant access to the video history of this entity's movement through the warehouse, where any contact with the personnel took place.

                Group 2. Compliance with the issued task when working on the mezzanine

                We are talking about a special part of the warehouse, where, as a rule, there are small and expensive goods. Working in this section of the warehouse, employees receive a task on their PDT (company WMS), which describes in which section of the warehouse and in which cell the employee should go to perform the task.

                From the point of view of the average person, there should be no problem, but in practice it is not so simple.
                  The "inattentive employee" option
                    The specialist went to the wrong section and, accordingly, begins to perform the wrong actions. In a good way, the employee should be prompted about this by the PDT itself, which will immediately block access. But this will only happen if this system is informed in time about all manipulations (what you took out, where you put it).
                      The "cunning employee" option
                        A specialist receives a task in one section, but deliberately goes to another one, where he commits illegal actions (for example, puts a couple dozen iPhones under his clothes or eats a kilo of expensive nuts).

                        To solve this group of problems, we used our main trump card, namely neural network robots. They get information from the accounting system and understand which employees have what tasks. This instantly makes a comparison - where are such employees, are they not in sections where they do not have tasks...

                        Moreover, if an employee is delayed in a certain section, the robot triggers an alarm (of course, in its own language) for further analysis. Well, and then the appropriate official examines the video, calls the employee for "questioning" and, having full information, makes a management decision.
                          Notifications of CVC system of detected violations in the company can be sent simultaneously to all designated persons: security officers, HR, the direct manager of operations, etc.

                          Group 3. Monitoring the work of outsourcing organizations

                          Our client, like a number of other companies of this level, uses the services of outsourcing organizations to "supply" personnel. Every day a different number of appropriate personnel come to the sites. It is reasonable to handle personnel matters in such a way, but it may cause difficulties with the fair calculation of wages.

                          The fact is that the cost of outsourcing company services is determined by the number of man-hours. But in fact the number of people and hours worked may be much less than was agreed upon. In practice, this happens all too often. For example, one person is registered several times (as a result, the company believes that 100 employees went out for a shift, but 90 actually work). There can also be another situation, when a person enters a facility, and then leaves on his own business. Outsourced workers are not always interested in a full day's work, and often, if possible, slack off. Tracking several thousand personnel with the help of simple video cameras is impossible in practice.

                          Our real-time facial recognition was used as a solution to this problem. The neural network robots recorded absolutely all incoming and outgoing people, determining the number of unique faces. Each face was linked to a specific outsourcing company. The productive time of each employee at the facility was recorded separately. Thus, if someone left the site, did not work enough, left work early - all this rightfully reduced the outsourcing company's check.
                            Important: Any suggestions of ready-made template solutions to implement neural network video analytics for B2B is a scam
                            Implementing neural network robots without immersing yourself in the customer's business processes is impossible to do. Any template solutions can work in an extreme case for B2C. And those companies that offer them in B2B are, to put it mildly, offering their customers nothing.
                            Every company has its own specific business processes. So from our side to go deep into client's processes is not only necessary but important. The client in this case was extremely ready for this. As a result, the third group of tasks, related to the outsourcing companies, arose in the course of work, when at one of the meetings we learned about this problem and offered to solve it.

                              Stages of integration (implementation)

                              Stage 1. Alignment of security policies.

                              Sometimes the approval may take a year, and sometimes it is fast. At any company, especially a large one, all information is confidential and usually it is very reluctant to be shared with outside companies. It is this point that always requires an explanation from our side.

                              In this case, the approval lasted a quarter. The main question is how the access to video will be organized on the pilot (who uploads it, what channels are available, etc.).

                                Stage 2. Preparation of datasets, robot training

                                Working with the camera angles which the customer already had, we prepared models and conducted docking. The first docking revealed some strange things about the customer's database. It took us several weeks to figure out where some of the data was lost and why it was happening.

                                  Stage 3. Piloting (one month).

                                  The pilot project was implemented with limited functionality (the program worked on two gates). This result was enough for the customer to see what we had agreed to show initially.
                                    It took us 6 months from startup to delivery of the pilot project.
                                    The pilot project is a ready-made software, which captures all the necessary information online: something was not delivered, unloaded in a wrong place... Up to the fact that according to the documents it was unloaded, but in fact it was not in this place. Or the opposite situation: there was unloading, but no documents for the operation, etc. It took us 6 months from startup to delivery of the pilot project.

                                    The result of the case: the scaling and continuation of work

                                    As we indicated above, for this client, we can not operate with specific indicators, but we give you our word of honor that this is not a trick. Perhaps in the future this information will be made public.

                                    For ourselves, we always evaluate our work according to two criteria,

                                    1. How quickly the customer decides to move from a pilot project to scale;
                                    2. How the customer accepts the financial terms of the main project.

                                    All decisions, including closing financials, were made within days. And on the final amount of the main project, they did not even try to bargain with us (by the way, we never bargain ourselves).
                                    Scaling up is always a simpler task, because the particular business is already studied, and the main aspects for implementing neural network robots have been implemented.

                                    The main time is spent on organizational issues on the part of the customer (e.g., the purchase of equipment that is missing, the purchase and delivery to the site of the server).

                                    Subject to the customer's obligations for the equipment, the time to scale can take 7-9 working days per center. But during this time, we can work with ten centers in parallel.

                                    Customer's opinion: "It wasn't as expensive as we thought..."

                                    As usual, we asked for feedback from the client on the completion of the pilot project. We would like to highlight two misconceptions that the client had prior to the result. We want to talk about them, as they are relevant to all participants in the market, the consumers of video analytics.

                                    Delusion 1: It won't work

                                    We claim it will work! To be sure of this, it is enough to open the production of any "live" object and see it with your own eyes. We have a lot of production cases where you can see that it works.

                                    Delusion 2. High price

                                    Voicing the cost of such systems, we always see the pleasant surprise of our customers. It's cheaper than they thought. And cheaper than they've heard from those they've asked before contacting us.
                                    We're interested in customers who are willing to set industry standards
                                    Two years ago, we were working with a variety of customers - bakeries, pancake houses, grocery stores. But we already know the industries that are getting a tremendous effect, and can scale. These are the automobile business (car wash chains, service stations, car centers, production), production facilities, and logistics. They are the priority for us, because it is a question of controlling people, not machines or products.

                                    If a company comes to us today that, for example, owns dining cars, and offers to monitor the kitchen, we will refuse. Because all of our attention is directed to where we can create and set the industry standard. That's really interesting.

                                    A year ago we mastered the implementation of neural network video analytics in the car business; now we have about 10% of all car centers in the country. We are projected to sign up another 50% within a year. And now we are introducing an industrial standard of neural network video analytics in logistics.

                                    And another thing... an industrial standard cannot be expensive. It has to be affordable, and it definitely will be.
                                    Please note that you do not need to be a huge logistics center to implement neural networks and work with our company. What matters here is not so much the size of the company, but the desire to be at the forefront of modern technology. So if you have an ordinary, even a small warehouse, but you plan to develop, you are welcome.
                                    If our philosophy is close to you and you want to be the company, the quality of which will be equal to the whole industry, then please call. We will evaluate your situation and tell you how you can increase profits with CVC neural network video analytics.

                                    Call before your competitors do!
                                    Cyber Vision Control
                                    CVC mitigates losses in any business, however small or big it is, whether it is a manufacturing enterprise
                                    or a service company.

                                    20 days
                                    Average pay-off period after CVC has been implemented
                                    >10 mln
                                    >100 mln
                                    Disciplinary violations detected
                                    Economic violations detected
                                    Read related
                                    Industry Solutions | Cases | Blog | About| Contact Us

                                    +7 (800) 301-39-70 contact@cvc.ai

                                    3, ul. Mira, ROOM 1H, St. Petersburg, 197101, Russia

                                    POWER AICONTROL© LLC
                                    OGRN (company number) 1197847127125

                                    Privacy policy