What’s wrong with this video? Hint: look at the Inspector’s results for width / height.
Unfortunately, the answer in many people’s minds is …. nothing. I can’t begin to count the number of videos and images in BOLOs that attempt to depict a scene that looks quite like the one above. If you don’t know what you’re looking at, it’s hard to say what’s actually wrong with this video.
We’re back from the Axon Accelerate Conference. What an incredible experience to meet so many law enforcement professionals who are enthusiastic about going from Capture to the Courtroom with reliable tools based in science and fact, not tools repurposed from the art world.
I’d like to share today the answer to a question posed to us at the Conference. The question was, “how do you quickly get rid of that annoying orange color cast that you find in images / videos taken in underground locations or grow houses.”
The answer is the Temperature Tint filter (found in the Adjust filter group). But, before we look at the filter and how it works, let’s talk about about Colour Temperature.
The chart above is from my old book, Forensic Photoshop. It’s helpful to look at colour temperature from the standpoint of the Sun as it rises – the horizon going from warm to cool. Another way to look at colour temperature is with the chart below that places temperature (the Planckian locus in Kelvin) as it relates to the CIE XYZ Color Space.
If you’ve wondered at the filters in the Extract Filter group and asked yourself, what are these for, you’re not alone. Depending on your specific use case with Amped FIVE, there are likely a few filters for which you have no use in your current context. Others, you may use in a very specific way each time – but others may use them differently.
Thus it is that I encountered a request for a feature that’s been in Amped FIVE for quite some time. I’ve responded to the request with details on how to accomplish the task. Now, I’ll expand on the question and share a more detailed look at an often overlooked filter – Add Text. (click on the images to see the full-res versions)
We work in the field of forensic video analysis, which is generally intended as the analysis of the images themselves and their context in a legal setting. For this reason, our customers often ask us if our products are valid for court use and if they have been validated and certified. We have written this post as an answer to the most common questions related to this topic.
You can also download this as a PDF document here.
What are the scientific foundations of Amped Software products?
All the processes implemented in our software follow the principles of scientific methodology. Any process follows these basic principles:
- Accuracy (Reliability): our tools and training program help users avoid processing errors caused by the implementation of an inappropriate tool or workflow and help mitigate the impact of human factors / bias.
- Repeatability: the same process, executed by the same user at a different time, must lead to the same result. The project format in Amped FIVE, for example, does not save any image data. Every time a project is reopened, all the processing happens again starting from the original data. In the event that a project file is lost or as a part of a validation or other test scenario, the same user can repeat the steps and settings, guided by the tool’s report, and achieve the same results.
- Reproducibility: another user with the proper competency, should be able to reproduce the same results. Amped FIVE generates a complete report detailing all the steps of the processing, the settings / parameters applied, a description of the algorithms employed in the processing and the scientific references for those algorithms (when applicable). In this way, another user, with a different tool set or by implementing the same algorithms, should be able to reproduce the same results. Given the huge number of implementation details and possible differences, it is not expected to produce a bit by bit copy of the results, but only to produce an image of similar informative content.
Additionally, we apply strict due diligence on the applicability of the algorithms for the forensic environment. Not every algorithm is, in fact, properly applicable in a forensic science setting. We cannot use algorithms which have a random component because they would not be reproducible and repeatable (when we do, we set a fixed seed for the random number generation) and we cannot use algorithms which “add” external data to the original, for example improving the quality of a face with information added from an average face. All information is derived from the actual evidence file.
We employ algorithms which have been validated by the scientific community through peer review, such as university textbooks, scientific publications, or conference papers. If for some specific task, there are not good enough algorithms available or we need to adapt existing algorithms, we describe the algorithm and attempt to publish them in scientific journals. Continue reading
One of the things that fascinate me the most in forensic video analysis is the relation between the subjective digital data and the objective human interpretation involved in any investigation. Psychological biases and the fallacies of human perceptions easily verifiable with any of the popular optical illusions are just some of the factors which must be taken into account while doing investigations.
But this time I want to look at things from a higher level and talk about the usefulness of video as evidence and our perception of it. Chances are you have already seen the very interesting article: “The Value of CCTV Surveillance Cameras as an Investigative Tool: An Empirical Analysis” (link).
The abstract provides some impressive numbers: “This study sought to establish how often CCTV provides useful evidence and how this is affected by circumstances, analysing 251,195 crimes recorded by British Transport Police that occurred on the British railway network between 2011 and 2015. CCTV was available to investigators in 45% of cases and judged to be useful in 29% (65% of cases in which it was available).”
For reference, this is the decision workflow used in the classification (image from the above paper).
This really made me feel good. It looks like what we are doing here at Amped Software is having an impact on society, and more than we expected. I think most people in our community would be surprised by the numbers. At Amped, we see hundreds of cases every year, and for more than half of the images and videos that we receive, we just say that they are useless. Continue reading
A crime has occurred. Your investigators comb the area looking for clues. Your media relations staff hit the airwaves asking for the public’s help. Your social media cyber team trolls the Internet for images taken about the time of the crime and in the general location.
An image shows up on social media that was taken a few minutes before the crime occurred, looking down the street at what is now your crime scene. But, what’s wrong with this picture?
Taken into the setting sun, the features of the scene are back-lit. Useful information is lost.
Or is it? Continue reading
When a driver wraps his car around a tree, the damage is likely rather obvious. Same again for a head-on collision at high speed. There’s not much car left to repair, so the insurance companies will likely pay out on the policy.
But in today’s app-driven world, minor dents and scratches are now being handled by the policy holder through the use of mobile device apps. Simply snap a picture or video of the damage and upload it to the insurance company. Claims are processed the same day and your money arrives quickly. Folks love this mobile claims processing functionality so much that insurance companies are featuring their time-saving apps in their advertising.
Whilst customers love this convenience, so do crooks. It turns out that fraudsters are using photo editing software to create fake photo evidence in support of bogus claims. This type of activity affects all policy holders as losses are spread out across all customers, keeping rates higher than they should be in a fraud-free world.
Enter Amped Software.
Without naming names (I don’t want to ruin the fraud-catchers’ fun), our software is being employed as both a risk management function (catching fraud), as well as to assist claims processors when folks turn in proprietary CCTV files in support of claims. Continue reading
Back in 2009, an article in the North Dakota Law Review noted the following about the use of drones by law enforcement, “The widespread use of Unmanned Aerial Vehicles (UAVs) and Unmanned Aerial Systems (UASs) in domestic law enforcement is imminent. Every police department, chief, and beat officer in the United States dreams of the ability to have eyes everywhere—a constant panoramic view of every angle in every precinct with the ability to instantly zoom in on suspicious behavior. That ability is available now. And it is on sale, cheap.”
That was 2009. We haven’t seen a surge in the use of drones by US law enforcement agencies. As the author noted at the time, “[t]he problem is regulatory uncertainty surrounding operations of UAVs in American airspace, and no one wants to be the guinea pig. The Federal Aviation Administration (FAA), tasked with ensuring the safe and orderly operation of aircraft, is regulating UAV operations of the kind that domestic law enforcement wants. The FAA has effectively stopped domestic law enforcement agencies from operating small UAVs in their operations without running afoul of FAA regulations for now.”
US Law Enforcement Agencies Using Drones
The market for dedicated UAVs and UASs hasn’t really materialized in the way that other equipment markets, like body worn cameras, has. In the absence of such a manufacturing segment, the few police agencies that have decided to deploy drones, like the Los Angeles Sheriff’s Department, are generally choosing to buy consumer-oriented models.
Everyone has a mobile phone …
A crime has occurred. What’s the first thing that people around the scene do? They grab their mobile phones. Why? To call the police or emergency services? Not usually. Not at first.
First things first.
They want to go viral on social media.
But it’s dark, and the person holding the phone is excited and moving around.
They capture the events and eventually send it to you. But it seems worthless. How can you make sense of this dark, shaking, video?
After the attacks of Paris, Brussels (and unfortunately many others), three days ago there was another major event at Istanbul Airport. While its origin is yet to be officially confirmed, strong hints are again at ISIS terror strategy. The number of victims is currently set at more than 40 and growing, with more than 160 persons injured. This is, again and again, a very sad story and our prayers are with the victims, the wounded and their family.
As usual, in these major events, it is interesting to analyze the different audio and video sources and their use. Continue reading