Ontology for a Panoptes building: exploiting contextual information and smart camera network

Tracking #: 1714-2926

Roberto Marroquin
Julien Dubois
Christophe Nicolle

Responsible editor: 
Guest Editors ST Built Environment 2017

Submission type: 
Full Paper
The contextual information in the built environment is highly heterogeneous, it goes from static information (e.g., information about the building structure) to dynamic information (e.g., user’s space-time information, sensors detections and events that occurred). This paper proposes to semantically fuse the building contextual information with extracted data from a smart camera network by using ontologies and semantic web technologies. The developed ontology allows interoperability between the different contextual data and enables, without human interaction, real-time event detections to be performed and system reconfigurations. The use of semantic knowledge in multi-camera monitoring systems guarantees the protection of the user’s privacy by not sending nor saving any image, just extracting the knowledge from them. This paper presents a new approach to develop a "all-seeing" smart building, where the global system is the first step to attempt to provide Artificial Intelligence (AI) to a building.
Full PDF Version: 

Minor Revision

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Florian Vandecasteele submitted on 20/Sep/2017
Minor Revision
Review Comment:

This manuscript was submitted as 'full paper' and should be reviewed along the usual dimensions for research contributions which include (1) originality, (2) significance of the results, and (3) quality of writing.

Firstly, the authors reformatted the paper according to the comments made during the first revision cycle. Still some better formatting/ lay-out could be done to further increase the readability.

Secondly, I would suggest the authors to included a comparison for the false positive and negative detections with and without the proposed WiseNet architecture. Furthermore, the authors mention that the system could implement several image processing algorithms. It should be stated more clearly which alternatives are available.

Thirdly, there are some small language/typing errors, the following list is not limited:
- of sight -> of field-of-view
- assignment of values should satisfied -> should satisfy
- rules was adapted -> rules were adapted

Finally, if would encourage the authors to include the IFC file in their online demonstrator and if possible to make the software open-source.

Review #2
Anonymous submitted on 22/Oct/2017
Minor Revision
Review Comment:

The paper has been improved and addresses theoretical, technological and practical issues related to the use of semantic web in real world applications. Therefore it’s worth of publication.
One remaining critical aspect is related to the use of English language. There are still several errors throughout the paper. A serious proof reading by an English-speaking person is needed. For instance:
- Pg.2, 4: There is difference in the meaning of especially, specially and specifically
- Pg.3, rephrase “A context-aware system in the built environment is a complex task”. A system is not a task.
- Pg.3, “For example, the required event… their location”. An event doesn’t have a location.
- Pg.4, 8: “consists on” is not correct.
- Pg.5: “inserting data to the ontology” -> “inserting data into the ontology”
- Pg.5 “the ontology developing process” -> “the ontology development process”
- Pg.5: “determine the scope of the ontology…”
- Pg.6: missing subject in “Roughly, is knowledge about…”
- Pg.10: “the IFC file must contain the following entities” -> “the IFC file must contain instances of the following entities”
- Pg.10: “… for the extraction, were” -> “… for the extraction, where”
- Pg.13: “object is people”. “People” is a plural noun.
- Pg.15: “empirically threshold” -> “empirical threshold” or “empirically set threshold”
- Pg.16: “PIS-E is an specific time-space” -> “PIS-E is a specific time-space”
- Pg.17: “The central API process” -> “The central API processes”
- Pg.19: “when the system do not detects” -> “when the system does not detect”
- Pg.20: “this could be consider as” -> “this could be considered as”
- Pg.21: “expected to overcomes” -> “expected to overcome”

Other comments:
- Sect.4.1. Which version of the ssn ontology is adopted?
- Links to “http://wisenet.checksem.fr/#/ontology” could be added as footnote or proper references.
- Sect.5.: “This population is performed only once at the initialization of the system…”. What if there is a reconfiguration of the building?
- Sect.5 and following: the use of “full-ifcowl” is somehow misleading since it recalls the concept of OWL Full ontology
- Sect.5.2: “This process needs to be repeated for all the rows of the extracted table…”. Isn’t possible any optimization?
- The title of Section 7 could be reworked
- Sect.7.2: it would be interesting to read also results about the performance of the system to execute the various steps in the workflow.
Finally a few more references could be added to the work, since the scope is quite broad.
- Any paper addressing the problem of MCBS in critical environments such as banks, casinos, etc.?
- Works related to spatial reasoning, for instance refer to publications by Mehul Bhatt
- Any reference to the myth of Panoptes?
- Since a modified version of ifcOWL ontology is actually employed in the wisenet system, it could be taken in consideration to use the ontologies developed in the scope of the W3C Community Group Linked Building Data (LBD). See references [a][b]

[a] M. H. Rasmussen, P. Pauwels, C. A. Hvid, and J. Karlshøj. Proposing a Central AEC Ontology that allows for Domain Specific Extensions. In LC3 2017: Volume I Proceedings of the Joint Conference on Computing in Construction (JC3), pages 237–244, Heraklion, Greece, July 2017.
[b] W. Terkaj, G. F. Schneider, and P. Pauwels. Reusing domain ontologies in linked building data: the case of building automation and control. In Proceedings of the 8th International Workshop on Formal Ontologies Meet Industry, 2017.