Slashdot Mirror
Digital Camera Could Help Sort Fish, Save Stocks
MountainSplash writes "PlanetArk.com is carrying a story about a new camera that "takes a digital photograph of the catch which is then divided into a grid, allowing a computer to measure the shape and color of each fish in the grid. It needs one tenth of a second and identifies 98 percent of fish correctly." The claim is that fish can then be culled quicker possibly increasing the likelyhood of survival for the incidental catch in the net. Testing is being done by Norway's Institute of Marine Research and Norwegian marine electronics maker Scantrol. Onboard testing has proven highly successful, but underwater attempts still need more work. With everything we have all been seeing computers do the last few years, I personally found this to be one of the more interesting of late."
And i first read it would recognize socks - would be a great invention if built-in in laundrys: Never loose a second sock or try to find the one you are missing !
Spelling mistakes: My is english spoken not tongue of mother.
I'd be forced to add cartoon drawings of 'charlie' from starkist into the 'endangered' database
Somehow I doubt that there will be much of a migration into any kind of system such as this. A large proportion of the fishing industry uses as little technology as possible as break-downs cannot be repaired until the ship returns to port, maybe not until after then. That would mean a large amount of losses for a fishing company. There is no point over complicating things that can be achieved simpily.
The story fails to mention when and how the picture is taken. I believe for this to be effective, no two fishes must be too close nor on top of each other. Anyone has more technical details on the process?
DrkBr
Aside from the pun, the camera can be linked to a sorting device - so that it can .... what? NOT dump the fish? Also, this reduces the waste to ... 25% - down from 33% - not a gigantic saving. Every little bit helps.
All in all, short on detail, and how it will reduce waste, lets see them sort the fish and reject the unwanted ones BEFORE the die from exhaustion on board
Johns: Well, how does it look now? Riddick: Looks clear.
...but I seriously doubt that the fishing industry will adopt this without legislative mandate. What happens now is that when fisherman haul in a catch, they sort out all prohibited/undersireable fish. They throw overboard that bycatch regardless is the fish are alive or dead. There is no record of what their bycatch was and they suffer no consequences for this bycatch. With this system, there is now a record of the bycatch and it will provide empirical proof of the bycatch problem and therefore ammo to those looking to clean up the fishing industry.
Who are you? The new #2 Who is #1? You are #617565. I am not a number, I am a free man! Muhahaha.
If only the system could help sort trolls on Slashdot. *Sigh*
Everyone knows socks morph into boxers/briefs (whatever you use) during laundry.
Think about it, you run out of paired socks but you rarely run out of boxers.
---- Take the Space Quiz!
This is just one example of the increased power of automated pattern recognition. Once computers reach a level of vision close to humans, we will se an explosion in automated tasks. Other examples include Sony Aibos vision, lip-reading software that helps in speech recognition, 'robot scientists' and the next generation of speech recognition with the potential to revolutionize human computer interaction. HAL, is that you?
Is the real problem that we're killing too many of the fishes we didn't intend to catch? Or is it that we're catching too many fish?
Don't forget that quick sorting is only part of the problem, not the whole thing. Another important factor is that fish are wounded/damaged by the nets even if they are smaller than the holes, they lose scales and the wounds get infected (hence they end up dying anyway). This has been somewhat improved with modern nets but still needs work.
Anyway, props to them with this new system. Despite what the tree-huggers may say, we need the fishing industry to feed ourselves, and the better we can catch the appropiate fish while leaving the rest undisturbed, the better.
---- Take the Space Quiz!
Bah. Fish! How do you sell crap like that?
Now, if it could crawl the net, and find stuff matching your preferences... hell, think of the oceans of time I would stop wasting looking for quality pr0n and "+5 funny" posts.
Gee, I wonder what kind of pattern matching/classification algorithm it is using. 98% is pretty damn high. Really high. That is a very robust algorithm indeed.
If it can be applied to fish, it can be applied to nearly any kind of object that needs to be identified. I would really like more technical details, as I am very sceptical of this 98% business.
Searching for 'automatic "fish classification"' doesn't turn up much...
I'm guessing it's a neural network or some other sort of classifier that has been trained with existing pictures of fish.
The Official Steve Ballmer Webpage
Hmmm...I'd read this as being more useful for scientific studies of fish stocks, rather than for the fishing industry. I mean, I'm sure both would find it useful, but the cost and reliability issues would rule it out for the majority of fishermen, as a few other posters have already said.
Good technology for scientists, especially if they are keen on returning live fish to the sea as far as is possible. Fish stock estimation is pretty unreliable as is, at least in the UK. Maybe something like this would help.
Meine Schwester ist sehr, sehr reizvoll - Nietzsche
IAACVPS (I Am A Computer Vision Ph.D. Student), and I'd like to add some general remarks concerning this application, and concerning computer vision in general.
Although the article mentions a nice application of computer vision, it is shockingly sparse in details. This in itself is not so strange for a news-site, but the fact that they didn't include a link to a more detailed description is a pity.
Some ideas:
First, the article doesn't make sufficiently clear whether one looks at the net, full of fish, or that one looks at the fish all spread out on a flat surface. If one looks at a full net, one can only see the fish on the outside, i.e., only a small fraction: that doesn't provide any information on the fish on the inside. If one looks at the fish spread out on a flat surface, one can see all the fish, but there are a number of issues here:
Given the speed at which they process, it's most likely that they determine fish-size based on general statistical properties in different regions of the image. In that case, the 90-something% accuracy really doesn't mean that much, because in all honesty, I don't see how they can either measure or guarantee that. Looks like marketing optimism to me.
Now, on the general state of computer vision: If you're expecting terminator-like all-seeing computer in the near future, don't hold your breath! It might take some time:
At the moment, some object classes that don't vary too much in structure within the class (e.g., faces, cars, people), can be found reasonably quickly and moderately reliably in an image. To give an example, the detection of human faces in 800x600 images can be done in about a second, with about a 90-95% detection rate, but with about 1-10 false positive detections per image. That effectively means that if you find a face, there still is only a 30% change that it's actually a face.
In order to understand what you see, you rely on high-level semantics. These include the geometrical arrangement of objects (e.g., your head stands on top of your body, there is a hierarchy body->limbs->extremities, etc.) and general relations (e.g. finding faces at eye-level, so e.g. near the horizon). Research on these higher-level semantics is really in its infancy: the main problem is that it's very hard to get enough "world-knowledge" into the computer for it to make all the relations.
I can put a nice multiple-frame face-detection demo here, but that would destroy my research group's net-connection. If someone can offer a high-bandwidth spot, mail me: I'll then make a movie available.
Support a Europe-related section on Slashdot!
so we can recognize fish but not faces? this is the same technology that so miserably fails to recognize faces in real life but works so marvelously in marketting demonstrations.
so what is the big deal; now you can verify what you knew was happening anyway? maybe if the camera had a robotic arm that yanked the offender out of the net and put it directly in my can of "Chicken of the Sea"...
stop being so fucking greedy with your satellite fish finders and 5 mile fishing nets
i have absolutely no sympathy for industries that through only their own greed and short term stupidity put themselves out of buisness, fishing had survived for thousands of years till fish finders,5 mile nets, 10000 ton ships etc etc, you don't have to be a fucking genius to work out their real problems are, and they think taking pictures will help them
the phrase "did they really think it would last forever"
comes to mind
of course greed is the behaviour mankind will realise is wrong after we have pissed away all earths natural resources and we are left sitting on a dust ball wondering what happened
A>S
The problem is that there are too many damn whales, eating all the fish :-/ (they propose a simple solution).
Whale... let it in
tuna... back to the sea
The company I worked for a couple years back was a seafood company. I worked at a clam processing plant and they used digital camera's and computer software to take a picture of each clam as it went along the conveyor belt. The computer then graded the clam depending on size and colour. They have been using this process for atleast 4 to 5 years now.
The Good Life
The whole thing sounds fishy to me.
I know for a fact that a similar system, have been developed in the late 90's for estimating the weight of fish inside a fish cage. This is good because knowing the size and distribution of fish in stock makes planning of food, harvest insurance etc much simpler. This system uses simple pattern recognition for separating the farmed fish from intruders etc. I would imagine such a system becoming very useful for the fish farming industry where separation in size etc is an issue.
M.
--
incuso
Ok, there goes:
Face Detection .torrent.
Ok, PLEASE leave your client open: I don't want my connection killed! ;)
Support a Europe-related section on Slashdot!
We didnt have such a problem. All our socks were red and distributed EVENLY among the citizens.
This perpetual motion machine Lisa made is a joke, it just keeps getting faster and faster. - Homer
The number of endangered and protected species slaughtered by Japan's massive fishing industry is appaling. And the Japanese government thinks its A-O-K, as long as the price of sushi stays down. Maybe this system could help stop overfishing/killing of certain species which aren't harvested for food anyway.
Not sure if they would even bother though. Japan is one of only two countries that refuses to respect the international whaling treaty. Endangered whale meat is sold on store shelves, and sometimes even in public school food.
Recently, a pair of foreigners were given extremely harsh jail sentences after documenting on video a local town's annual slaughter of thousands of protected dolphins. The local superstition blamed the dolphins for the ever-diminishing stocks of native fish. No, overfishing couldn't have anything to do with it, could it?
(A bit off-topic, but the Japanese government is also constantly raising the considered-safe mercury level, due to heavy industry runoff of mercury into the sea. By international health standards, eating one fish from the Japan sea can contain as much as one month's safe mercury dose. Pretty scary, to those of us who live there.)
When I was in the Navy, my ship went into the shipyard for an overhaul - among the equipment scheduled for repair was one of the ship's massive clothes dryers. When the tumbler was removed from its spindle, repair workers found... you guessed it... an enormous bundle of yarn wrapped around the spindle - the remains of uncounted socks the dryer had "eaten" over the years.
No kidding.
Sean
The problems come from the large factory trawlers. Because of the way the fish asphyxiate in the trawler nets, there is no advantage to sorting them. In fact, some larger vessels grind the dead fish to chum to avoid having incriminating dead fish floating on the surface. In contrast, smaller operations (say a 2 man boat at the smallest), line fish and pull in many km of hooked line. This means that as they pull the fish in by hand, if it is the wrong sort or size, they let it drop. If it is the right size and sort, they gaff it and pull it in. Salt water fish are quite tough and likely to survive the former. One flatfish made the local papers and earned a retirement in the local aquarium by virtue of surviving about 12 hours out of water.
If the trawling process is allowed to continue and if it is modified so that the fish are brought on board live, then the digital camera sorting would be very useful.
Beta is broken and the link to classic doesn't work. Stop wasting our time or there won't be anybody left here.
Drastically reduce commercial fishing, if it cannot be eliminated altogether.
This isn't just another vegetarian / vegan rant. I've nothing against anybody eating all the beef, lamb, pork and so on they want. Or even a few fish, if they caught them themselves. But commercial fishing is ruining the sea.
Land meat is generally farmed. That is, for every pig that gets turned into sausages, at least one pig is raised to replace it. {The exception is game, but we can assume due to its comparative rarity from the dinner table that humans accounts for a tolerable proportion of predation of such species. The same would apply to fish if commercial fishing were reduced or eliminated} This is merely a consequence of private ownership of land; but it is a happy one.
When someone takes a fish out of the ocean, what steps do they take to ensure that another fish will replace it? Even the most hardened capitalist can see that privatising the oceans is never going to work.
Land meat is usually slaughtered quickly. This is a pragmatic, rather than strictly humane, requirement -- you generally don't want to annoy a pig or cow, lest it attempt to retaliate with the full force of its fight-or-flight response adrenalin rush; but the consequences are, again, fortunate.
And yet there are still people who claim they are "vegetarians"; yet they persist in eating fish, which have spent their lives ingesting toxic heavy metals which their bodies cannot excrete, died slowly of suffocation on the deck of a trawler, and not been replaced to ensure a supply for future generations.
Je fume. Tu fumes. Nous fûmes!
Tell your story walkin', dumbass, animals are FOOD. Get over it.
This is 98% accurate. That means it makes 2 mistakes for each 100 fish.
The main problem with the computer facial recognition systems is the vast number of faces they wanted to have it vet each day. If that system were as accurate as this one and vetted 1,000 faces each day you would have 10 false alarms each day. Not too useful.
In reality, I think the face systems were more accurate than this. But they still aren't accurate enough to be useful.
I saw a PBS special some time ago on salmon migration. There are special "fish ladders" that allow the salmon to swim upstream around the dams. On many of the ladders, they have an area where fish swim past a window. People sit in front of these windows and count each type of fish as they go past.
I wonder if this technology has replaced that process. I also wonder how effective it is at separating different breeds of the same type of fish. (If I remember there were many different "breeds" of salmon, that were just slightly distinct visually from eachother)
Do I hear dead Romans, laughing ?
The simple summary of recent fisheries history is that we are destroying stock after stock, around the world. For more on this, I recommend a Nature paper by my colleague Ransom Myers, entitled "Rapid worldwide depletion of predatory fish communities" [Nature 2003, vol 423: p280-283]. The paper is somewhat technical, but even if your Statistics are a bit rusty, check out Figure 2, which shows a world map of depletion. To give you a gist (and a chill up your spine), here's a quote from the paper: "Industrialized fisheries typically reduced community biomass by 80% within 15 years of exploitation."
If you don't have an online subscription to Nature.com, you can find the paper and related papers at Myers' website http://fish.dal.ca/~myers
This HAS been done by us. They are late. The proposed method will not work, it is to arbitrary, low tech and yealds a sucsess percentage on about 70% Pall Fagraberg Marine Tech www.marine-tech.fo