<p><strong>Abstract.</strong> Building floor plans with locations of safety, security and energy assets such as IoT sensors, thermostats, fire sprinklers, EXIT signs, fire alarms, smoke detectors, routers etc. are vital for climate control, emergency security, safety, and maintenance of building infrastructure. Existing approaches to building survey are manual, and usually involve an operator with a clipboard and pen, or a tablet enumerating and localizing assets in each room. In this paper, we propose an interactive method for a human operator to use an app on a smart phone to (a) create the 2D layout of a room, (b) detect assets of interest, and (c) localize them within the layout. We use deep learning methods to train a neural network to recognize assets of interest, and use human in the loop interactive methods to correct erroneous recognitions by the networks. These corrections are then used to improve the accuracy of the system over time as the inspector moves from one room to another in a given building or from one building to the next; this progressive training and testing mechanism makes our system useful in building inspection scenarios where a given class of assets in a building are same instantiation of that object category, thus reducing the problem to instance, rather than category recognition. Experiments show our proposed method to achieve accuracy rate of 76% for testing 102 objects across 10 classes.</p>

Light propagation in photoreceptor outer segments is affected by photopigment absorption and the phototransduction amplification cascade. Photopigment absorption has been studied using retinal densitometry, while recently, optoretinography (ORG) has provided an avenue to probe changes in outer segment optical path length due to phototransduction. With adaptive optics (AO), both densitometry and ORG have been used for cone spectral classification based on the differential bleaching signatures of the three cone types. Here, we characterize cone classification by ORG, implemented in an AO line-scan optical coherence tomography (OCT), and compare it against densitometry. The cone mosaics of five color normal subjects were classified using ORG showing high probability (∼0.99), low error (<0.22%), high test-retest reliability (∼97%), and short imaging durations (< 1 hour). Of these, the cone spectral assignments in two subjects were compared against AO-scanning laser opthalmoscope densitometry. High agreement (mean: 91%) was observed between the two modalities in these two subjects, with measurements conducted 6-7 years apart. Overall, ORG benefits from higher sensitivity and dynamic range to probe cone photopigments compared to densitometry, and thus provides greater fidelity for cone spectral classification.

Light propagation in photoreceptor outer segments is affected by photopigment absorption and the phototransduction amplification cascade. Photopigment absorption has been studied using retinal densitometry, while recently, optoretinography (ORG) has provided an avenue to probe changes in outer segment optical path length due to phototransduction. With adaptive optics (AO), both densitometry and ORG have been used for cone spectral classification, based on the differential bleaching signatures of the three cone types. Here, we characterize cone classification by ORG, implemented in an AO line-scan OCT and compare it against densitometry. The cone mosaics of five color normal subjects were classified using ORG showing high probability (~0.99), low error (<0.22%), high test-retest reliability (~97%) and short imaging durations (< 1 hour). Of these, the cone spectral assignments in two subjects were compared against AOSLO densitometry. High agreement (mean: 91%) was observed between the two modalities in these 2 subjects, with measurements conducted 6-7 years apart. Overall, ORG benefits from higher sensitivity and dynamic range to probe cone photopigments compared to densitometry, and thus provides greater fidelity for cone spectral classification.