Monocular depth estimation methods traditionally train deep models to infer depth directly from RGB pixels. This implicit learning often overlooks explicit monocular cues that the human visual system relies on, such as occlusion boundaries, shading, and perspective. Rather than expecting a network to discover these cues unaided, we present ThirdEye, a cue-aware pipeline that deliberately supplies each cue through specialised, pre-trained, and frozen networks. These cues are fused in a three-stage cortical hierarchy (V1->V2->V3) equipped with a key-value working-memory module that weights them by reliability. An adaptive-bins transformer head then produces a high-resolution disparity map. Because the cue experts are frozen, ThirdEye inherits large amounts of external supervision while requiring only modest fine-tuning. This extended version provides additional architectural detail, neuroscientific motivation, and an expanded experimental protocol; quantitative results will appear in a future revision.

The automated real-time recognition of unexpected situations plays a crucial role in the safety of autonomous vehicles, especially in unsupported and unpredictable scenarios. This paper evaluates different Bayesian uncertainty quantification methods from the deep learning domain for the anticipatory testing of safety-critical misbehaviours during system-level simulation-based testing. Specifically, we compute uncertainty scores as the vehicle executes, following the intuition that high uncertainty scores are indicative of unsupported runtime conditions that can be used to distinguish safe from failure-inducing driving behaviors. In our study, we conducted an evaluation of the effectiveness and computational overhead associated with two Bayesian uncertainty quantification methods, namely MC- Dropout and Deep Ensembles, for misbehaviour avoidance. Overall, for three benchmarks from the Udacity simulator comprising both out-of-distribution and unsafe conditions introduced via mutation testing, both methods successfully detected a high number of out-of-bounds episodes providing early warnings several seconds in advance, outperforming two state-of-the-art misbehaviour prediction methods based on autoencoders and attention maps in terms of effectiveness and efficiency. Notably, Deep Ensembles detected most misbehaviours without any false alarms and did so even when employing a relatively small number of models, making them computationally feasible for real-time detection. Our findings suggest that incorporating uncertainty quantification methods is a viable approach for building fail-safe mechanisms in deep neural network-based autonomous vehicles.

Welcome to the supermarkets of the future. They may look and feel like the supermarkets we are all used to – and stock the same bread, butter and bananas – but these shops are now fitted out with more than £1m of the latest technology that their bosses promise will put an end to our biggest frustration (queueing) and our most persistent crime (shoplifting). Jill French, a legal secretary in her 30s, wearing a sharp navy suit and matching beret, has just left a Tesco Express on London's Holborn Viaduct empty-handed. It's coming up to 6.30pm on a Thursday and, like dozens of others, French has popped in for a few essentials on her way home. "I just went in to grab pasta, milk and some broccoli," she says.

Opinions expressed by Forbes Contributors are their own. The author is a Forbes contributor. The opinions expressed are those of the writer. For the last two years, my team and I have been building and commercializing a product that empowers the visually impaired by recognizing what they are looking at using computer vision. Now, ThirdEye is being acquired by TheBlindGuide (see TechCrunch release here).

Opinions expressed by Forbes Contributors are their own. The author is a Forbes contributor. The opinions expressed are those of the writer. For the last two years, my team and I have been building and commercializing a product that empowers the visually impaired by recognizing what they are looking at using computer vision. Now, ThirdEye is being acquired by TheBlindGuide.

Amidst the free t-shirts and apps to help you find parties on campus always lie a few hidden gems for those with the patience to hunt. ThirdEye, one of those gems forged out of PennApps, UPenn's hackathon, is being acquired today by TheBlindGuide for an undisclosed sum. Started by three current Penn students, ThirdEye brings object recognition to mobile to help the visually impaired. Originally created as an add-on for the now obsolete Google Glass, the ThirdEye of today exists as a mobile app. It uses Google's Cloud Vision API to identify objects and read their descriptions aurally.