# Tag Info

9

Google’s self-driving car most likely uses mapping of traffic signs using google street view images for roadway inventory management. If traffic signs are not in its database, it can still “see” and detect moving objects which can be distinguished from the presence of certain stationary objects, like traffic lights. So its software can classify objects based ...

4

https://www.technologyreview.com/s/530276/hidden-obstacles-for-googles-self-driving-cars/ Google’s cars can detect and respond to stop signs that aren't on its map, a feature that was introduced to deal with temporary signs used at construction sites. But in a complex situation like at an unmapped four-way stop the car might fall back to slow, extra ...

4

The .weights seems to be the extension for a framework called "darknet" , you can read h5 files with Keras , however it if you really want to build an object detection framework there is no necessity to stick the darknet's weights. There are many pretrained models lying around in the web. Or else you could finetune a pretrained imagenet model in Keras which ...

3

No. YOLO and SSD are based on Nvidia's proprietary CUDA technology which is not available on Raspberry simply because of the GPU vendor is not Nvidia. Even more, there seems to be no implementation of even OpenCL for the Raspberry's GPU. What you can do is to try port YOLO's of SSD's CNN core from CUDA to Raspberry GPU's assembler, in the way described in, ...

3

According to your example: Trees will likely be in the bottom half of the image. Still, you will not know whether there will be one, two or five trees. Thanks to translation invariance property of CNN's, each tree will activate filters responsible for tree detection. You still need to handle those few exceptions where trees are on hill. To achieve better ...

3

I just want to provide this intuition this NN consists of a 2 steps detection pipeline (the region proposal and regression + classification in parallel) exploring a certain range of scales and aspect ratios for proposals as the proposed region is rectangular and the objects of interests have not a rectangular appearance strictly speaking, but a mostly ...

3

The AI of the car uses sensor data to process all the data and classifies objects based on the size, shape and movement patterns. It can recognize surroundings from a 360 degree perspective by making predictions about vehicles, people and objects around it will move. It can detect pedestrians, but as moving, column-shaped blurs of pixels, so it really ...

3

So I am assuming that you are trying to detect a lego brick from the image. One idea is that you can use transfer learning. Leveraging a pre-trained machine learning model is called transfer learning. The underlying idea behind transfer learning is that one takes a well-trained model from one dataset or domain, and applies it to a new one. François Chollet ...

3

TL;DR This is possible. You need a correctly labeled dataset. Your dataset has two labels: $y\in \{\text{background},\text{object in frame}\}$ or simply $y\in \{0,1\}$ This labelling avoids needing to know what object is in frame only that there is an object in frame. Examples With Similar Objectives Here as a paper (link) that was seeking to classify ...

2

They may be just for fun. If you had a robot that understood you, could hold a conversation with you about your interests, and even had goals of its own (good or bad), it wouldn't really need to do anything special. People would buy it like it was a toy or game. Also, they might be usable as programmers, artists, designers, anything creative that a computer ...

2

The terms you are looking for are deeplearning and convolutional neural networks for object detection. Google responds well to these terms. From academical point of view you can start from: Single shot multibox detector: https://arxiv.org/pdf/1512.02325v5.pdf Or Faster-RCNN: https://arxiv.org/pdf/1506.01497.pdf These are not simple architectures and there ...

2

Object detection is a regression of the bounding box (rectangle) around the object. In this way, the two ways you suggest are equivalent. What I suggest you to look at is lane detection for self-driving cars - a well studied problem. It seems that this is a very relevant task (if not the same), so its solution should work for you as well.

2

I think you're describing "object localization and detection" which combines object identification with discovery of its spatial placement in the field of view. There's been a lot of work on this in the past 5 years using CNNs and variants. It's very much in demand for pedestrian/obstruction detection, identification, and avoidance in autonomous car ...

2

Pixel based object recognition, like the name says, works by analyzing the individual pixels of an image. For example: You analyze an image with a lot of different shades of blue and some grey pixels - you might assume that this is the picture of a plane in the sky or a ship in the water. You could also look for similar pictures by calculating the ...

2

From your question I can assume you are a beginner in the field of AI. Welcome to this exciting field. To answer your question, we have not yet been able to create a truly artificially intelligent program. They are all apparently intelligent but are just a set of simple/complex rules. An artificially intelligent agent must have at-least 2 aspects in the ...

2

in effect the midpoint it's contained in cell 2. Cells 1,3,4 will shown a Pc=0 according to the Y.O.L.O. algorithm which only takes in count the cell that contains the midpoint and calculates the bounding box, as you mentioned, with by bx, by, bh, bw. With the proposition of Y = [1, 0.9, 0.1, 2, 2], I would think that if you take the point (0,0) as the left-...

2

If you want to get experience, you should probably start with some easier task. Object detection and localization is relatively hard and writing neural network and image processing pipeline from scratch will take you a long time. If you want to build up intuition how NN's work, you might want to code some simple task from scratch. This is an example. ...

2

I usually start with some papers and look at the references: Counting people using video cameras Sheng-Fuu Lin, Jaw-Yeh Chen, Hung-Xin Chao, Estimation of Number of People in Crowded Scenes Using Perspective Transformation, IEEE Transactions on Systems, Man and Cybernetics, November 2001, Part A, Vol. 31, Issue 6, pp. 645-654. A. C. Davies, J. H. Yin,...

2

In my thesis I actually solve the problem of depth estimation with a CNN based on a single monocular image so I can share my experiences for understanding that problem. As you already stated in general you have the problem that you cannot recover the scale of the scene in an image by geometrical approaches directly. And that is still not the case even if ...

2

There is actually no definition for a perfect loss curve. It varies according to the dataset, the classification problem, the dropout rate, the learning rate and the optimizer used. The loss should not decrease suddenly , which might be a sign of overfitting. It also should not take long time to decrease, or else it will take years to converge.

2

Cartesian Bias and Pipeline Efficiency You are experiencing a techno-cultural artifact of Cartesian-centric imaging running all the way back to the dawn of coordinate systems. It is the momentum of practice as a consequence of applying Cartesian 2D coordinates to rasterize images appearing at the focal planes of lenses from the dawn of television and the ...

2

A understanding for this level of abstraction is technically possible. It is not hard to create an AI able to count. Unfortunately, this does not imply that the AI knows what 1 is. It knows: This is 1 piece of cake and this is 1 sheet of paper. But the idea of the number is not grasped yet. Also, animals can count, but they do not understand why it works. ...

2

A bounding box is a rectangle superimposed over an image within which all important features of a particular object is expected to reside. It's purpose is to reduce the range of search for those object features and thereby conserve computing resources: Allocation of memory, processors, cores, processing time, some other resource, or a combination of them. ...

2

The minimal algorithm for convolution in $\mathbb{R}^2$ is a four dimensional iteration. for all vertical kernel positions for all horizontal kernel positions initialize the value at the output position to the bias for all vertical positions in the kernel for all horizontal positions in the kernel add the product of the input value ...

2

FastAI is the most “out of the box” API for this type of task. For video examples (and a little theory) check out the MOOC section of their site. Practical Deep Learning and Cutting Edge Deep Learning are the two sections most relevant to you. But if you want a working implementation check out this GitHub repo that implements SSD for your purposes. I ...

2

Try lowering the learning rate. Such a loss curve can be indicative of a high learning rate. Due to a high learning rate the algorithm can take large steps in the direction of the gradient and miss the local minima. Then it will try to come back to the minima in the next step and overshoot it again. You may also try switching to a momentum-based GD ...

2

Overview As it has already been observed, your main problem, beside the training related issues like fixing the learning rate, is you have basically no chance to learn such a big model woth such a small dataset ... from scratch So focusing on the real problem, here are some techniques you could use dataset augmentation transfer learning from a ...

2

In this case, you have an ontology and want to learn the ontology. There are many researches in this topic that you can find. However, the data could be the most challenging part. Some of the researches: Ontology learning for the Semantic Web Ontology Learning Also, as these are some frameworks to ontology learning, you can use deep networks such as RNN‌ ...

2

I'm working on a similar problem. I'm using a 2D point cloud of an object, for example, X and Y coordinates for height, and with that more simple data set I will train a regression model (currently working on that). In my opinion, this approach with dissecting complex point cloud into cross sections that contain wanted dimension and feeding that to the model ...

2

This could be possible, providing you have the right dataset to train it on. The volume of a cup consist of width, height and depth. You can probably detect all three of those given the bounding box or the pixels of the cup. However detecting the dimensions of an object require a reference object, like a penny or your finger and you have to specify the ...

Only top voted, non community-wiki answers of a minimum length are eligible