Deficiencies of Manual Systems

Traditional approaches to Security and Surveillance rely on indiscriminate filming and manual processing, which are frequently proven to be costly and ineffective. Disparate data sources, information delivered in incompatible formats, and the inability to automate processes and interactions, mean that traditional approaches often miss or fail to pick up important events and identify potential threats to security, or malpractice within the organization. To overcome these shortfalls, resources can be added but this is far from the optimal solution.

The overall efficacy of any CCTV system is entirely dependent upon the extent to which individuals are able to recognize and respond to the video surveillance signals presented to them. Human error accounts for virtually all failures to respond appropriately to video surveillance signals. Recent industry figures suggest that up to 85% of on-screen information goes unnoticed once a system operator has been on duty for a mere fifteen minutes, rendering a typical CCTV system desperately inefficient.

Multiple duties and discontinuity in personnel, such as shift changes and high staff turnover, contribute to reduced efficiency and dramatically decrease the quality of surveillance operations. In addition, failures in concentration and consciousness can impact greatly. Human concentration span typically wanes after 45 minutes according to recent scientific studies. Typical surveillance shifts lasting up to 12 hours and far exceed the normal human concentration span and contribute significantly to failures to identify and respond to unusual, illegal or suspicious behaviors. Even when an operator is fully focused on a surveillance task, a number of low level failures in the human consciousness are responsible for failure to detect important activity.

The fundamental issue is that traditional security systems do not actually understand what is occurring or how it might relate to other events that have occurred in the local vicinity during a short time period. Relationships can therefore not be identified using traditional approaches. Additionally, they cannot effectively describe the footage for real-time reporting or later reuse it as part of a case or investigation. To really manage this data, security systems need a new way to process information, moving away from manually monitoring and tagging video footage to an approach whereby computers can understand the information and process it in the same way a human would – that is, by comprehending their meaning and using past experience to make a more appropriate experience.

Attention Span

Multiple duties and discontinuity in personnel, such as shift changes and high staff turnover, contribute to reduced efficiency and dramatically decrease the quality of surveillance operations. In addition, failures in concentration and consciousness can impact greatly. Human concentration span typically wanes after 45 minutes according to recent scientific studies. Typical surveillance shifts lasting up to 12 hours far exceed the normal human concentration span and contribute significantly to failures to identify and respond to unusual behaviors.

Blindness

Visual disruption within a scene, such as switching between multiple screens, can result in vital information being missed. Furthermore, when the brain is focused on one particular activity, for example, counting vehicles leaving a car park, it will frequently become unable to respond to other stimuli, resulting in events being missed in the time it takes to transfer concentration from one activity to the other.

Change blindness: visual disruption within a scene e.g. switching between multiple screens or blinking, can result in vital information being missed;
Attention blindness: when the brain is focused on one particular activity, for example, counting vehicles leaving a car park, it will frequently become unable to respond to other stimuli;
Attention blink: when the brain shifts its focus from one activity to another, events can be missed in the time it takes to transfer concentration from one activity to the other;
Repetition blindness: repeated sequences of similar items can cause some events to be missed.

Subjective

Once video and other data sources are indexed into the system, retrieving the correct information also presents the user with a challenge. This is because traditional indexing methods rely on human defined metatags.

Each person will categorize or tag a given file differently. In order to retrieve it, a user must guess the category under which it was tagged. Two authors of similar information may view it very differently from one another, and differently again from those searching for the information. This often results in the need for a complex searching process that misses the targeted video content.

The problem inherent in this approach is that humans can get lax in their tagging, leading to the large majority of content being tagged with default tags, making it difficult to find specific content and rendering the whole taxonomy system useless.

Language Dependent

Keywords are inherently dependent on the local language system. Across a global enterprise, relevant documents from regional departments that are entirely similar might never be collocated together based on the language used to tag them. Additionally, folksonomies invite deliberately idiosyncratic tagging, which is not necessarily a problem in the consumer sphere, but in the professional environment it can mislead the user and dramatically decrease retrieval rates.

Apathy

One of the most stubborn issues is that of employee apathy. While professional taxonomists may engage in organizing and metatagging with quasi-religious zeal, many employees are less enthused by the process. This will often lead to tags being too general, missing, or simply incorrect.

Keyword and Boolean Searches

The most common information retrieval techniques, keyword and Boolean search, require users to input the exact words they are looking for into a text field. Upon submission, a search will return a list of files that contain the search terms. This will only be successful if the user running the search uses the exact same word that was applied to the content at the time of index.

Not Scalable

In order to be very specific in the retrieval and processing of tagged files, the number of tags will need to be very high. For example, tag numbers in a company such as Reuters run into the tens of thousands. However, as the number of tags increases, so does the effort required and the likelihood of misclassification.

High Labor Costs

Taxonomy creation and tagging is still a predominantly manual task requiring input from librarians, users and IT staff. This means that large labor costs are involved in making sense of information.

Idea Distancing

Tags also fail to highlight the relationships between subjects. There are often vital relationships between seemingly separately tagged subjects such as wing design/low drag and aerofoil/efficiency, a concept known as “idea distancing.”

Obviously, there will be a degree of overlap between these categories, and because of this a user may be interested in the contents of both. However, without understanding the meanings of the category names there is no clear correlation between the two.

Interoperability of Tagging

XML is not a set of standard tag definitions; it is a set of definitions that allow users to define tags. This means that if two organizations are going to interoperate and apply the same meaning to the same tags, they have to explicitly agree upon their definitions in advance. While this may prove possible for small groups of cooperating agents working over public networks, doubts remain as to whether this will scale to support an extended network of industry trading partners.